> Miguel Wrote:
>
> I installed RTLinux on my AMDk6 430 MHZ with 128 Mb RAM and
> up to now I've just
> been probing with the example programs.
> I have tried the hello.c with various thread periods and
> observed that when I
> try periods of less than 10us my system crashes. Is this a
> normal limit?
That is fairly typical of most PC architecture boards. I've never
tried to run much faster than 40KHz but have had no trouble getting to that
speed. Others have reported systems going as fast as 100KHz, but I have not
heard of much faster than that.
> Is it
> a
> hardware limit or is it an RTLinux limit?
Yes. It is a combination of the hardware interrupt latency and the
time to run the RTLinux scheduler. If your card can generate an interrupt
you may be able to go a little faster if you do all your work in your ISR
(which is generally not a good practice). At that point you are almost
entirely hardware limited. Just be sure to leave some time for Linux.
> If I can't schedule periodic threads with less than 10us
> period that will mean
> that if the thread is used to aquire samples from a DAQ board
> I will have a
> 100KHz sampling rate limit, which I find a bit low for my
> needs.
> Is it possible
> to achieve higher sampling rates with RTLinux?
There are so many options here I really can't suggest anything
without knowing more about what you want to do. If you really need 100KHz
control (not just sampling), then you probably have to go to a system with a
better interrupt structure than the IBM PC or most other general purpose
computers. I would recommend investigating some of the faster DSP solutions
and rolling up your sleeves and getting ready for a long and painful
development experience.
If, on the other hand, you want to sample at 100KHz but do not need
to generate control outputs at that rate I would recommend finding a DAQ
board with some on-board memory. In that case you wake up your RTLinux
process as often as required by your control problem and read all the
samples from the board. An example of this might be a system that is trying
to control some process that is happening at 30KHz but which only has a few
KHz of bandwidth. In that case you would want to sample at 100KHz but
updating your control output at 10KHz would be more than sufficient.
Regards,
Steve Cohen
--------------------------
Stephen D. Cohen
Engineering Manager
Xybion Sensor Positioning Systems
11528 53rd Street North
Clearwater, FL 33760
Voice: (727) 299-0150
Fax: (727) 299-0804
[EMAIL PROTECTED]
www.xybion.com
************************************************************************
THIS EMAIL, AND ANY ATTACHMENTS, CONTAINS CONFIDENTIAL AND PRIVILEGED INFORMATION
INTENDED FOR THE USE OF THE ADDRESSEE. IF YOU ARE NOT THE INTENDED RECIPIENT OR AN
AUTHORIZED REPRESENTATIVE OF THE RECIPIENT, DO NOT READ OR DISTRIBUTE THE CONTENTS OF
THIS EMAIL AND DELETE IT FROM YOUR SYSTEM. THIS EMAIL AND ALL ATTACHMENTS HAVE BEEN
SCANNED FOR VIRUSES AND ARE BELIEVED TO BE VIRUS FREE. HOWEVER, IT IS THE RECIPIENT'S
RESPONSIBILITY TO ENSURE THAT THEY ARE VIRUS FREE. XYBION DOES NOT ACCEPT ANY
RESPONSIBILITY FOR ANY LOSS OR DAMAGE ARISING IN ANY WAY FROM USE OF THIS EMAIL AND
ATTACHMENTS. XYBION ALSO DOES NOT ACCEPT RESPONSIBILITY FOR PERSONAL EMAIL OR EMAIL
NOT ASSOCIATED WITH ITS BUSINESS PURPOSES.
************************************************************************
-- [rtl] ---
To unsubscribe:
echo "unsubscribe rtl" | mail [EMAIL PROTECTED] OR
echo "unsubscribe rtl <Your_email>" | mail [EMAIL PROTECTED]
--
For more information on Real-Time Linux see:
http://www.rtlinux.org/
