[Xenomai-help] Re: Latencies due to RT-Socket-CAN register accesses

[Wolfgang Grandegger <wg@domain.hid>]

Roland Tollenaar wrote:
> HI Wolfgang,
> 
>> It was the IXXAT PCI card currently plugged into my test PC but I 
>> actually recommand the PEAK PCI card. It's also much cheaper, I guess. 
>> Tomorrow I'm going to repeat the tests with this card ... stay tuned.
> Clear. Thanks for the advice.

Here is a revised list of the register access times:

PEAK-Dongle: register read : 11705ns (  85428/sec)
PEAK-Dongle: register write: 11687ns (  85562/sec)

IXXAT-PCI  : register read :   725ns (1378643/sec)
IXXAT-PCI  : register write:   301ns (3311667/sec)

PEAK-PCI   : register read :   486ns (2057468/sec)
PEAK-PCI   : register write:   161ns (6201956/sec)

>>> I will continue development on my laptop with the dongle for the time 
>>> being. It would be interesting to see what happens to the latency 
>>> after your proposed changes are in effect.

Non-CAN latencies will not be significantly affected but RT-Socket-CAN 
latencies will be worse due to overhead of interrupt handling by the 
service task.

>> BTW, what are the latencies you measure on your system under load 
>> (without RT-Socket-CAN).
> Off the top of my head 25us average 30us to 35us max. I am not sure I am 
> "loading" the system though. How do I measure this load that is always 
> talked about?
> 
> Roland
> 
> 
>>
>> Wolfgang.
>>
>>> Thanks,
>>>
>>> Roland
>>>
>>>
>>>
>>> Wolfgang Grandegger wrote:
>>>> Hallo,
>>>>
>>>> in the meantime I have measured the latencies introduced through 
>>>> messages sent and received by RT-Socket-CAN. The SJA1000 register 
>>>> access times on my rather old PC with an Athlon 1100 Mhz are:
>>>>
>>>> PEAK-Dongle: read  access: 11807 ns
>>>> PEAK-Dongle: write access: 11677 ns
>>>>
>>>> IXXAT-PCI  : read  access:   729 ns
>>>> IXXAT-PCI  : write access:   305 ns
>>>>
>>>> I measured an increase of the latency of approx. 170us with the 
>>>> PEAK-Dongle and approx 13us with the IXXAT-PCI card for the 
>>>> reception of a full CAN message (with 8 bytes payload). Sending 
>>>> messages is a bit less disturbing. I have attached a small patch to 
>>>> measure the SJA1000 register access times when the driver is 
>>>> initialized. You are welcome to apply it on your setup and report 
>>>> the results. I'm especially interested in numbers for the ISA bus 
>>>> (or PC-104).
>>>>
>>>> Wolfgang.
>>>>
>>>>
>>>>
>>>> ------------------------------------------------------------------------ 
>>>>
>>>>
>>>> + diff -u xenomai/ksrc/drivers/can/rtcan_dev.c.IOTEST 
>>>> xenomai/ksrc/drivers/can/rtcan_dev.c
>>>> + diff -u xenomai/ksrc/drivers/can/sja1000/rtcan_sja1000.c.IOTEST 
>>>> xenomai/ksrc/drivers/can/sja1000/rtcan_sja1000.c
>>>> --- xenomai/ksrc/drivers/can/sja1000/rtcan_sja1000.c.IOTEST    
>>>> 2007-02-26 09:17:27.000000000 +0100
>>>> +++ xenomai/ksrc/drivers/can/sja1000/rtcan_sja1000.c    2007-03-13 
>>>> 10:01:47.000000000 +0100
>>>> @@ -728,6 +728,30 @@
>>>>      if (chip == NULL)
>>>>      return -EINVAL;
>>>>  
>>>> +#if 1
>>>> +    {
>>>> +    nanosecs_abs_t begin, diff;
>>>> +    volatile u8 reg;
>>>> +    int i, count = 100000;
>>>> +    begin = rtdm_clock_read();
>>>> +    for (i = 0; i < count; i++) {
>>>> +        reg = chip->read_reg(dev, 0);
>>>> +    }
>>>> +    diff = rtdm_clock_read() - begin;
>>>> +    printk("%s: register read time for %d accessed: %ld (%ld per 
>>>> access)\n",
>>>> +           dev->board_name, count,
>>>> +           (unsigned long)diff, (unsigned long)diff / count);
>>>> +    begin = rtdm_clock_read();
>>>> +    for (i = 0; i < count; i++) {
>>>> +        chip->write_reg(dev, 0, reg);
>>>> +    }
>>>> +    diff = rtdm_clock_read() - begin;
>>>> +    printk("%s: register write time for %d accessed: %ld (%ld per 
>>>> access)\n",
>>>> +           dev->board_name, count,
>>>> +           (unsigned long)diff, (unsigned long)diff / count);
>>>> +    }
>>>> +#endif
>>>> +
>>>>      /* Set dummy state for following call */
>>>>      dev->state = CAN_STATE_ACTIVE;
>>>>      /* Enter reset mode */
>>>
>>>
>>
>>
> 
>