[Etherlab-users] ecrt_master_receive big latency

[zy]

Dear Etherlab users,

         I use the lateset igh with 
unofficial patchset under Linux-3.18.20 and Xenomai-2.6.5. My NIC is Intel 
i211.My question is, when I run a simple sample, there is no error even if the 
running time is very long. I just use QtCreator and make the configuration of 
slave and igh real-time cycling thread to a dynamic library, I find there is a 
big latency of calling ecrt_master_receive. My testing method is like this:

 

RTIME begin=rt_time_read();

ecrt_master_receive(master);

ecrt_domain_process(domain);

RTIME end=rt_time_read();

 

The latency (end-begin) will reach 1.5ms about 30 minutes after starting the 
program. Except this error, almost latency is under 10us. At the same time, I 
execute ??cat /proc/xenomai/faults?? and find there will be page fault. I alse 
execute ??cat /proc/xenomai/stat?? and find MSW of the real-time thread 
increases. And there will also be ??UNMATCHED Datagram?? and ??Datagram XXX 
(domain0-0-main) was SKIPPED XX times?? message log.

 

My real-time thread is:

   while(1) {

       wakeupTime = timespec_add(wakeupTime, 
cycletime);

       clock_nanosleep(CLOCK_TO_USE, 
TIMER_ABSTIME, &wakeupTime, NULL);

 

       begin_r=rt_timer_read();

       ecrt_master_receive(master);

       ecrt_domain_process(domain1);

       end_r=rt_timer_read();

       receive_time=end_r-begin_r;

       if(receive_time>max_receive_time)

           max_receive_time=receive_time;

            temp[0]=EC_READ_U16(domain1_pd
 + offset.status_word_6041_0);

            
temp[1]=EC_READ_U32(domain1_pd + offset.position_actual_value_6064_0);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;if(once<=800)
 {target_position=temp[1];once++;}

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
 &nbsp;&nbsp;if(temp[0] == 0x218){

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EC_WRITE_U16(domain1_pd+offset.control_word_6040_0,
 0x0080 );

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;else if( (temp[0]&amp;0x004f) == 
0x0040&nbsp;&nbsp;){&nbsp;&nbsp;//temp[0]==0x250

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EC_WRITE_U16(domain1_pd+offset.control_word_6040_0,
 0x0006 );

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;//printf("1.state
 = %x\n",temp[0]);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;else if( (temp[0]&amp;0x006f) == 
0x0021){ //temp[0]==0x231

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EC_WRITE_U16(domain1_pd+offset.control_word_6040_0,
 0x0007 );

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;//printf("2.state
 = %x\n",temp[0]);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;else if( (temp[0]&amp;0x06f) == 
0x023){ //temp[0]==0x233

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EC_WRITE_U8(domain1_pd+offset.modes_operation_6060_0,
 8);//csp mode

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EC_WRITE_S32(domain1_pd+offset.target_position_607a_0,target_position);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EC_WRITE_U16(domain1_pd+offset.control_word_6040_0,
 0x000f);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;else if( (temp[0]&amp;0x06f) == 
0x027){//temp[0]=0x237

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EC_WRITE_S32(domain1_pd+offset.target_position_607a_0,target_position);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 
&nbsp;&nbsp;EC_WRITE_U16(domain1_pd+offset.control_word_6040_0, 0x001f);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
 &nbsp;&nbsp;target_position+=0;

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;if (sync_ref_counter) {

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;sync_ref_counter--;

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;} else {

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;sync_ref_counter
 = 1; // sync every cycle

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
 
&nbsp;&nbsp;clock_gettime(CLOCK_TO_USE,&amp;time);&nbsp;&nbsp;&nbsp;&nbsp;//added
 by me&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; &nbsp;

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
 &nbsp;&nbsp;ecrt_master_sync_reference_clock_to(master, TIMESPEC2NS(time));

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;}

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;ecrt_master_sync_slave_clocks(master);

&nbsp;

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;begin_s=rt_timer_read();

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;//send process data

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;ecrt_domain_queue(domain1);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;//ecrt_domain_queue(domain2);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;ecrt_master_send(master);

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;end_s=rt_timer_read();

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;send_time=end_s-begin_s;

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
 &nbsp;

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;if(send_time&gt;max_send_time)

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;max_send_time=send_time;

&nbsp; &nbsp;&nbsp;}

&nbsp;

I check all the possible problem I think:

1. Using libethercat_rtdm.so and ec_igb.

2. Make sure calling ecrt_master_receive after a period of time after calling 
ecrt_master_send. Sometimes,I find I use an elapsed time to call 
clock_nanosleep, that is because the latency of ecrt_master_receive.

3. Calling mlockall(MCL_CURRENT | MCL_FUTURE)

&nbsp;

Does anyone know how to solve this problem?

&nbsp;

Best regards

Zhou Yang
-- 
Etherlab-users mailing list
Etherlab-users@etherlab.org
https://lists.etherlab.org/mailman/listinfo/etherlab-users