I would say that avg latency of 32uS is very good and I would be skeptical of 
this result. I don’t know what cyclictest does, but I’m wondering what the CPU 
load is during this test. My guess is the CPU load is low and that is why you 
are getting 32uS. If the CPU load was high, I would expect the number to 
increase to 100uS or more. Even Xenomai, which has a dual kernel is only able 
to achieve 40uS under load. 

Regards,
John




> On Mar 30, 2016, at 11:38 PM, Victor WANG <wangvictor1...@gmail.com> wrote:
> 
> hello,
> 
> I use beaglebone black and install Linux Debian (Linux beaglebone 
> 4.4.6-bone-rt-r6 #1 PREEMPT RT Thu Mar 17 04:47:32 UTC 2016 armv7l 
> GNU/Linux), I want to test the characteristic of Real Time, so I use 
> cyclictest:
> 
> After "cyclictest -p 90 - m -c 0 -i 200 -n -h 100 -q -l 10000", I got:
> 
> # Total: 000010000
> # Min Latencies: 00012
> # Avg Latencies: 00032
> # Max Latencies: 00053
> # Histogram Overflows: 00000
> # Histogram Overflow at cycle number:
> # Thread 0:
> 
> The result means the average latencies is 32 us.
> 
> I wonder if it is normal or not? (In my opinion, it is a little wired, 
> because with the RT-preempt patch, it should be better than it.)
> 
> And if there is something wrong in the process, please tell me .
> 
> Thanks so much.
> 
> -- 
> For more options, visit http://beagleboard.org/discuss 
> <http://beagleboard.org/discuss>
> --- 
> You received this message because you are subscribed to the Google Groups 
> "BeagleBoard" group.
> To unsubscribe from this group and stop receiving emails from it, send an 
> email to beagleboard+unsubscr...@googlegroups.com 
> <mailto:beagleboard+unsubscr...@googlegroups.com>.
> For more options, visit https://groups.google.com/d/optout 
> <https://groups.google.com/d/optout>.

-- 
For more options, visit http://beagleboard.org/discuss
--- 
You received this message because you are subscribed to the Google Groups 
"BeagleBoard" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to beagleboard+unsubscr...@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to