ts-7000
[Top] [All Lists]

[ts-7000] Re: Scheduled activity on a TS-7800

To:
Subject: [ts-7000] Re: Scheduled activity on a TS-7800
From: "charliem_1216" <>
Date: Fri, 20 Jun 2008 19:39:44 -0000
Hi --

--- In  "javierroitman" <> wrote:
>
> I think you are missing one important point. If you need to deal with 
> micro or even millisecond timing accuracy, you need a Real Time 
> Operating System, not Linux. Maybe you can install some of the 

Well, not to be pedantic, but not entirely so.  An RTOS is not
necessarily fast, but it is deterministic.  That is, an RTOS can
*guarantee* that events will be serviced in within a certain time, but
a standard OS can only make a best effort.  That response time may be
only 1 second, but it is guaranteed.  Granted, many RTOSs are fast as
well, but that's not what makes them RT.

> patches provided by TS to run a Real time kernel instead of the 
> regular Linux one. Then, you need to treat your data acquisition 
> tasks as real time.

Many folks are using the HRT framework and low latency features of the
2.6 kernel just for this case, where timekeeping precision and
accuracy is needed, but an occasional datapoint past the deadline is
not a life or death situation.

> If not, you will need a data acquisition card with timers and FIFO 
> buffers and take care of the timing issues in hardware. In this way, 
> you can read the FIFO using a standard Linux process.

This is another approach too, but high resolution timers can still be
useful here.

Regards, ........ Charlie

> 
> Javier////
> 
> --- In  "David Farrell" <davidjf2001@> 
> wrote:
> >
> > --- In  "Anouk Ahamitet" <snowcone27@> 
> wrote:
> > >
> > > 
> > > --- In  "charliem_1216" <charliem_1216@>
> > > wrote:
> > > 
> > > >... Better to fix your A/D code so it is insensitive to system 
> load.
> > > 
> > > We're working on it, but since ts-linux doesn't have very accurate
> > > timers (minimum usleep() appears to be almost 10 MILLISECONDS and 
> the
> > > min nanosleep() is about 3.5 MILLISECONDS) we're stuck doing a 
> busy wait
> > > on the built-in microsecond timer on the TS-7800 in order to get
> > > accurate (and fast) enough timing on our A/D operations (note: 
> we're
> > > using a 3rd party A/D, not one of  Technologic's because the TS 
> A/Ds
> > > don't support the input voltage ranges we require and/or don't 
> have
> > > enough resolution).
> > > 
> > 
> > Why not look at A/D PC/104 boards like those at www.mesanet.com
> > they have the timers on board and FIFOs.
> > 
> > You may also be able to use the TS-7800 high res timer to measure 
> the
> > exact time your sample was taken and interpolate to get the value of
> > the reading for the time you want. Don't wait on the timer, just 
> read it.
> > 
> > David.
> >
>



------------------------------------

Yahoo! Groups Links

<*> To visit your group on the web, go to:
    http://groups.yahoo.com/group/ts-7000/

<*> Your email settings:
    Individual Email | Traditional

<*> To change settings online go to:
    http://groups.yahoo.com/group/ts-7000/join
    (Yahoo! ID required)

<*> To change settings via email:
     
    

<*> To unsubscribe from this group, send an email to:
    

<*> Your use of Yahoo! Groups is subject to:
    http://docs.yahoo.com/info/terms/

<Prev in Thread] Current Thread [Next in Thread>
Admin

Disclaimer: Neither Andrew Taylor nor the University of NSW School of Computer and Engineering take any responsibility for the contents of this archive. It is purely a compilation of material sent by many people to the birding-aus mailing list. It has not been checked for accuracy nor its content verified in any way. If you wish to get material removed from the archive or have other queries about the archive e-mail Andrew Taylor at this address: andrewt@cse.unsw.EDU.AU