Re: 3.12.6-rt9 on AM335x (armv7)

[Matthias Fuchs <mfuchs@ma-fu.de>]

Hi,

after some chatting with Nicholas and being sure that I didn't do anything totally stupid
I would like to provide my current kernel config and a trace generated by "cyclictest ... -b500".

kernel config -> https://www.dropbox.com/s/zsud0b77xoosjm1/config
trace -> https://www.dropbox.com/s/5uf58oqo0qwcn4x/trace-cyclictest-2508us.txt

I still get max latencies of about 4000us on this TI AM335x system running 3.12.6-rt9 with
timers-do-not-raise-softirq-unconditionally.patch reverse applied.

sched_rt_runtime_us and sched_rt_period_us are identical. The system is idle during the test.
Rootfilesystem comes via NFS.

root@generic-armv7a:~# cat /proc/sys/kernel/sched_rt_runtime_us 
1000000
root@generic-armv7a:~# cat /proc/sys/kernel/sched_rt_period_us  
1000000

root@generic-armv7a:~# uname -a 
Linux generic-armv7a 3.12.6-rt9-dirty #3 SMP PREEMPT RT Sat Jan 4 23:01:19 CET 2014 armv7l GNU/Linux

root@generic-armv7a:~# ~/cyclictest -p99 -m -n -i200 -h400 -q -l100000 -b 500
# /dev/cpu_dma_latency set to 0us
INFO: debugfs mountpoint: /sys/kernel/debug/tracing/
could not set ftrace_enabled to 0
could not set tracing_max_latency to 0
# Histogram
...
# Total: 000018604
# Min Latencies: 00024
# Avg Latencies: 00158
# Max Latencies: 02508
# Histogram Overflows: 00212
# Histogram Overflow at cycle number:
# Thread 0: ...
...
# Thread Ids: 01126
# Break thread: 1126
# Break value: 2508

Does any of you have an idea where this big max. latency comes from?

Matthias

On 01/01/2014 05:37 PM, Matthias Fuchs wrote:
> Hi,
> 
> I did a setup with 3.12.6-rt9 kernel on a Beaglebone board
> with an TI AM335x CPU running at fixed 720MHz. The kernel uses the 
> omap2plus_defconfig configuration that comes with this kernel with 
> additional CONFIG_PREEMPT_RT_FULL switched on.
> 
> I am observing some strange max. latencies when comparing with kernel 
> 3.2.45-rt66. The results of a similiar system can be found on the OSADL lab
> site (https://www.osadl.org/Latency-plot-of-system-in-rack-7-slot.qa-latencyplot-r7s5.0.html).
> 
> With "cyclictest -p99 -m -n -i200 -h400 -q -l10000000" I get
> ...
> # Min Latencies: 00013
> # Avg Latencies: 00062
> # Max Latencies: 04664
> ...
> 
> Also the latency does not differ much from that when doing a flood ping against 
> the system as simple stress.
> 
> 3.2.45-rt66 comes with a max. latency of 118us! So I expect something to be wrong with 3.12.6-rt9
> at least on armv7 or especially this device (max. lat. 4664us).
> 
> I also noticed an issue with the on-chip ethernet when CONFIG_PREEMPT_RT_FULL is
> switched on with this kernel:
> 
> I also noticed that the 3.12.6-rt9 with enabled 
> [    2.817024] net eth0: initializing cpsw version 1.12 (0)
> [    2.825269] net eth0: phy found : id is : 0x7c0f1
> [    2.830713] libphy: PHY 4a101000.mdio:01 not found
> [    2.835777] net eth0: phy 4a101000.mdio:01 not found on slave 1
> [   12.846394] Waiting up to 110 more seconds for network.
> [   22.846147] Waiting up to 100 more seconds for network.
> ...
> 
> Finally networking is fine. But I need to wait for 110 seconds :-)
> 
> Prior testing with 3.12.6-rt9 I did the same test with 3.12.5-rt7. Same results.
> But without CONFIG_PREEMPT_RT_FULL I do not get this bringup delay. I could not do this 
> test with rt9 because it does not build without CONFIG_PREEMPT_RT_FULL!
> 
> Any ideas?
> 
> Matthias
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>