From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <4DBA8655.9050400@domain.hid> Date: Fri, 29 Apr 2011 11:35:17 +0200 From: Thierry Bultel MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="------------070606030900080203050009" Subject: [Xenomai-help] How to interpret /proc/xenomai/stat CPU time of threads with priority 0 List-Id: Help regarding installation and common use of Xenomai List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: xenomai@xenomai.org, Jean-Baptiste Tredez , Nicolas Mabire This is a multi-part message in MIME format. --------------070606030900080203050009 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Hi all, I was wondering if the displayed CPU time was, for these particular threads, the only time spent in primary mode, of the total amount of time spent on the CPU. I am namely currently debugging an application which has such kind of thread, with a period of 50ms, and that takes up to 23% of the CPU. That is bad, but not a real issue if that time is spent only in secondary mode, but I do not know how to figure it out. The mode switches frequency is equal to the period of my thread, since it uses rt_task_wait_period I am a little bit concerned, my fear is that secondary mode time would be counted in the ROOT task ... BTW, I am using version 2.5.2 (I know, it's old ;-) ). Any help would be appreciated. Thanks Thierry --------------070606030900080203050009 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Hi all,

I was wondering if the displayed CPU time was, for these particular threads,
the only time spent in primary mode, of the total amount of time spent on the CPU.

I am namely currently debugging an application which has such kind of thread,
with a period of 50ms, and that takes up to 23% of the CPU.
That is bad, but not a real issue if that time is spent only in secondary mode,
but I do not know how to figure it out.
The mode switches frequency is equal to the period of my thread, since it uses rt_task_wait_period

I am a little bit concerned, my fear is that secondary mode time would be counted in the ROOT task ...
BTW, I am using version 2.5.2 (I know, it's old ;-) ).

Any help would be appreciated.

Thanks
Thierry
 --------------070606030900080203050009--