Experimental Physics and
Industrial Control System

I did a quick test on my MVME 5100 vxWorks 5.5 system.

1. increasing sysCklRate to 5000 (maximum that vxWorks lets me do)
-> CPU load went up from 2.0% to 2.6%
2. add a ".0002 second" scan rate
-> CPU load went up to 7.3%
3. put some records on the scan:
 ai with "Soft Timestamp" support
 calc to get time interval
 calc to get maximum interval
-> CPU load went up to 27.0%

DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000399947 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000399947 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000400066 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000399947 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000400066 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000199914 sec
DZ:TIMEDIFF 0.000200033 sec
DZ:TIMEDIFF 0.000399947 sec
DZ:TIMEDIFF 0.000200033 sec

After boot:
DZ:MAXTIMEDIFF 0.021000028 sec

After reset to 0 and and some wait:
DZ:MAXTIMEDIFF 0.000400066 sec
DZ:MAXTIMEDIFF 0.000600100 sec
Suddenly after some minutes:
DZ:MAXTIMEDIFF 0.002032518 sec

This does not look very promising.

(DB is attached.)

Dirk


On 08.01.2014 17:20, Till Straumann wrote:

On 01/07/2014 02:19 PM, Andrew Johnson wrote:

Periodic scans are quite complicated, since they rely on the
underlying operating system to implement a delay timer and reschedule
the scan thread after the specific delay has elapsed. Most OSs don't
provide high accuracy delay scheduling, so I don't expect we will ever
be able to run periodic scan threads at 10KHz. - Andrew

As a matter of fact I don't think that 10kHz periodic scans are a big
problem for something like RTEMS
or linux (with RT_PREEMPT) on a reasonably fast CPU.

I just used a simple 'clock_nanosleep' based loop (based on code by
windriver, modified by myself)
which does something like

while ( 1 ) {
     /* get current time */
       clock_gettime( CLOCK_MONOTONIC, &wakeup );
     /* compute wakeup time 100us from now   */
       timespec_add_100us( &wakeup );
     /* sleep until wakeup time      */
       clock_nanosleep( CLOCK_MONOTONIC, TIMER_ABSTIME, &wakeup, NULL );
     /* see when we actually woke up */
       clock_gettime( CLOCK_MONOTONIC, &now );
     /* missed = now - wakeup        */
       timespec_diff( &missed, &now, &wakeup );

     compute_statistics( &missed );
}

for a bunch of threads (using the SCHED_FIFO scheduler).

On my laptop (vanilla kernel, no RT_PREEMPT) I observe worst-case
'missed' deadline of several milli-seconds
but even on that system the running average is between 5us..50us.

On a kernel patched with RT_PREEMPT I get a worst-case missed deadline
by ~10us (average around 3-4us)
after running for a few minutes (on a not heavily loaded intel core
i7-2655LE, 2.2 GHz).

I would expect RTEMS/vxWorks to even perform a bit better.

- Till

record (ai, "DZ:TIMESTAMP")
{
    field (DTYP, "Soft Timestamp")
    field (SCAN, ".0002 second")
    field (PREC, "9")
    field (EGU,  "sec")
    field (FLNK, "DZ:TIMEDIFF")
}

record (calc, "DZ:TIMEDIFF")
{
    field (INPA, "DZ:TIMEDIFF.B")
    field (INPB, "DZ:TIMESTAMP")
    field (CALC, "A?B-A:0")
    field (PREC, "9")
    field (EGU,  "sec")
    field (FLNK, "DZ:MAXTIMEDIFF")
}

record (calc, "DZ:MAXTIMEDIFF")
{
    field (INPA, "DZ:TIMEDIFF")
    field (INPB, "DZ:MAXTIMEDIFF")
    field (CALC, "A>B?A:B")
    field (PREC, "9")
    field (EGU,  "sec")
}

References:

Re: Increasing scan rate to 10 kHz Andrew Johnson

Re: Increasing scan rate to 10 kHz Till Straumann

Navigate by Date:

Prev: Re: Agilent 33522A Function / Arbitrary Waveform Generator Michael Johnson

Next: Re: Increasing scan rate to 10 kHz Andrew Johnson

Index: 1994  1995  1996  1997  1998  1999  2000  2001  2002  2003  2004  2005  2006  2007  2008  2009  2010  2011  2012  2013  <2014>  2015  2016  2017  2018  2019  2020  2021  2022  2023  2024 

Navigate by Thread:

Prev: Re: Increasing scan rate to 10 kHz Till Straumann

Next: A call to 'assert(capacity != 0)' by thread‏ Emmanuel Mayssat

Index: 1994  1995  1996  1997  1998  1999  2000  2001  2002  2003  2004  2005  2006  2007  2008  2009  2010  2011  2012  2013  <2014>  2015  2016  2017  2018  2019  2020  2021  2022  2023  2024