Raspberry Pi 4
23 Feb 2020 22:42 #158338
by MrGreg
Replied by MrGreg on topic Raspberry Pi 4
Hello
OK Cheers. Will do the lcnc install soon. and report back
rt-tests are part of Debian
So
apt install rt-tests
The stanza I used is kinda std. Gives min, avg, max...
Broad cli window to see all detail
More intimate detail in man pages & www
Seems that with every linux kernel iteration the realtime thing gets worse...
Having said that I found Stretch was circa 580uS So????
Good times are just around the corner....
Cheers
MrGreg
OK Cheers. Will do the lcnc install soon. and report back
rt-tests are part of Debian
So
apt install rt-tests
The stanza I used is kinda std. Gives min, avg, max...
Broad cli window to see all detail
More intimate detail in man pages & www
Seems that with every linux kernel iteration the realtime thing gets worse...
Having said that I found Stretch was circa 580uS So????
Good times are just around the corner....
Cheers
MrGreg
Please Log in or Create an account to join the conversation.
24 Feb 2020 13:20 #158377
by andypugh
I have been thinking that there could be a generalised driver for ARM boards where GPIO is accessed though mmap()
(which includes Pi)
I have also wondered about a schema for defining pins as simple strings. There is something like this already in the BSPI Mesa driver and the absolute encoders:
linuxcnc.org/docs/2.7/html/man/man9/host...%20Interface%20(SSI)
However that schema is not really optimal for a bidirectional GPIO port.
Maybe a string with:
x = disabled
o = output
v = inverted output
u = pulled-up input (and have in and in-not like other drivers have)
d = pulled-down input
Replied by andypugh on topic Raspberry Pi 4
There are other devices that can need generalized gpio driver. I want to allow other devices in the framework.
I have been thinking that there could be a generalised driver for ARM boards where GPIO is accessed though mmap()
(which includes Pi)
I have also wondered about a schema for defining pins as simple strings. There is something like this already in the BSPI Mesa driver and the absolute encoders:
linuxcnc.org/docs/2.7/html/man/man9/host...%20Interface%20(SSI)
However that schema is not really optimal for a bidirectional GPIO port.
Maybe a string with:
x = disabled
o = output
v = inverted output
u = pulled-up input (and have in and in-not like other drivers have)
d = pulled-down input
Please Log in or Create an account to join the conversation.
24 Feb 2020 17:25 #158398
by MrGreg
Replied by MrGreg on topic Raspberry Pi 4
Hello
OK Lcnc latency-test: 1ms servo
As per previous with rt-tests cyclic:
Hard labour- glxgears @ 1080p, web browser (Firefox) 4 tabs, javascript & stuff etc IE same as before.
Hmmmm
840uS
Bit of extra info, again same conditions as before.
CPU from panel monitor 72% steady +- 2
ditto temp 52deg steady +- 2 ( I have massive passive heatsink )
No activity on core4 ( you knew that ) circa 95% other 3
Similar jumps in latency as previous test
10~20mins 320uS
~ 40 mins 370uS
~ 70 mins 470uS
~90 mins 840uS
I wasn't actively doing anything when the last two jumps took place. Guess this is background tasks/H-keeping stuff?
Overall a slightly longer duration ~ 100mins
I couldn't say for sure whether the last large jump was captured before when doing cyclic test as the duration was slightly longer this time. The pattern and figures look quite similar, apart from the last.
More alchemy and magic needed. Not to mention time ...
What next?
Cheers
MrGreg
OK Lcnc latency-test: 1ms servo
As per previous with rt-tests cyclic:
Hard labour- glxgears @ 1080p, web browser (Firefox) 4 tabs, javascript & stuff etc IE same as before.
Hmmmm
840uS
Bit of extra info, again same conditions as before.
CPU from panel monitor 72% steady +- 2
ditto temp 52deg steady +- 2 ( I have massive passive heatsink )
No activity on core4 ( you knew that ) circa 95% other 3
Similar jumps in latency as previous test
10~20mins 320uS
~ 40 mins 370uS
~ 70 mins 470uS
~90 mins 840uS
I wasn't actively doing anything when the last two jumps took place. Guess this is background tasks/H-keeping stuff?
Overall a slightly longer duration ~ 100mins
I couldn't say for sure whether the last large jump was captured before when doing cyclic test as the duration was slightly longer this time. The pattern and figures look quite similar, apart from the last.
More alchemy and magic needed. Not to mention time ...
What next?
Cheers
MrGreg
Please Log in or Create an account to join the conversation.
- Mike_Eitel
- Offline
- Platinum Member
Less
More
- Posts: 1150
- Thank you received: 184
24 Feb 2020 18:08 #158403
by Mike_Eitel
Replied by Mike_Eitel on topic Raspberry Pi 4
@MrGreg
Have you run this via ssd
Mike
Have you run this via ssd
Mike
Please Log in or Create an account to join the conversation.
24 Feb 2020 18:18 - 24 Feb 2020 18:19 #158405
by MrGreg
Replied by MrGreg on topic Raspberry Pi 4
@ Mike
Err No
SD
Samsung Evo
Cheers
MrGreg
Err No
SD
Samsung Evo
Cheers
MrGreg
Last edit: 24 Feb 2020 18:19 by MrGreg. Reason: Wrong reply
Please Log in or Create an account to join the conversation.
- Mike_Eitel
- Offline
- Platinum Member
Less
More
- Posts: 1150
- Thank you received: 184
24 Feb 2020 20:53 #158419
by Mike_Eitel
Replied by Mike_Eitel on topic Raspberry Pi 4
Sorry, c'ant decrypt
Err No ??
The rest i interpret as you use SSD Samsung Evo
I was wondering if sometimes writing to the shdc card give those spikes. I decided not to use my pi4 as long as they have not yet realized the usb boot.
Thx Mike
Err No ??
The rest i interpret as you use SSD Samsung Evo
I was wondering if sometimes writing to the shdc card give those spikes. I decided not to use my pi4 as long as they have not yet realized the usb boot.
Thx Mike
Please Log in or Create an account to join the conversation.
24 Feb 2020 22:00 #158425
by MrGreg
Replied by MrGreg on topic Raspberry Pi 4
@ Mike
No, not an ssd
I am using a 32GB Samung Evo+ SDHC
Could be SD writes? I have the 4GB version, so no need to access swap.
Prob could throw some read/writes into the mix to emulate next time.
I'm looking at using rt-tests to do a latency trace. I'll post that up shortly.
Cheers
MrGreg
No, not an ssd
I am using a 32GB Samung Evo+ SDHC
Could be SD writes? I have the 4GB version, so no need to access swap.
Prob could throw some read/writes into the mix to emulate next time.
I'm looking at using rt-tests to do a latency trace. I'll post that up shortly.
Cheers
MrGreg
Please Log in or Create an account to join the conversation.
24 Feb 2020 22:55 #158426
by MrGreg
Replied by MrGreg on topic Raspberry Pi 4
Hello
Following on from previous
rt-tests can apparently do a latency trace.
See here foe info/example:
taste.tuxfamily.org/wiki/index.php?title..._source_of_latencies
And man page
manpages.debian.org/stretch/rt-tests/cyclictest.8.en.html
Just tried it
It works on Gene's RT kernel
Just a "simple" matter of finding and eliminating them.....
Well....Might be helpful? TBD
Cheers
MrGreg
Following on from previous
rt-tests can apparently do a latency trace.
See here foe info/example:
taste.tuxfamily.org/wiki/index.php?title..._source_of_latencies
And man page
manpages.debian.org/stretch/rt-tests/cyclictest.8.en.html
Just tried it
It works on Gene's RT kernel
Just a "simple" matter of finding and eliminating them.....
Well....Might be helpful? TBD
Cheers
MrGreg
Please Log in or Create an account to join the conversation.
26 Feb 2020 08:23 #158514
by tjtr33
Replied by tjtr33 on topic Raspberry Pi 4
Thx Andy,
I will read up on mmap and the way hostmot... handles gpio pins
I had thought of using an array og bytes, one byte per pin, with bits for each 'feature'
But i hant though of how users enter the information.
There a re a LOT of pins to describe on these various devices.
thx
tomp
I will read up on mmap and the way hostmot... handles gpio pins
I had thought of using an array og bytes, one byte per pin, with bits for each 'feature'
But i hant though of how users enter the information.
There a re a LOT of pins to describe on these various devices.
thx
tomp
Please Log in or Create an account to join the conversation.
26 Feb 2020 08:56 #158519
by tjtr33
Replied by tjtr33 on topic Raspberry Pi 4
MrGreg
I tested Genes and my own kernel a lot over the last 2 days
There's not a lot of difference between them
I built mine from JT's instruction on Feb9 ( so had some newer pkgs than JT had )
I have different monitor than Gene
I have the npt fix from samco
see
and i force 600mhz AFTER booting ( not automated yet)
sudo sh -c "echo -n 600000 > /sys/devices/system/cpu/cpufreq/policy0/scaling_min_freq"
sudo sh -c "echo -n 600000 > /sys/devices/system/cpu/cpufreq/policy0/scaling_max_freq"
sudo sh -c "echo -n performance > /sys/devices/system/cpu/cpufreq/policy0/scaling_governor"
My system is responsive and videos smooth enough for me (infrequent blips i cant blame on anyone in particular)
here what you can expect:
run
latency-test period
then
IF you really beat on the system
like 4glxgears, 2 resized to larger
and chromium browser showing youtube video full screen, then back to default size so you can see the katency dialog
>I< get 106 usecs ( very long test )
IF you are nice to it ))
like 4 glxgears, no resizing, hands in pocketses
>I< get 50uS ( 13 hrs )
and here's some pix...
conclusion: MY OWN
iF you use it like a 1 bladed swiss army knif, you wont be developing and surfing and gaming
and you rely on the DRO ( not gui ) during cutting
THEN you can use a rpi3 or 4 to controll a slower stepp using gpio
a medium speed stepper using PiCNC
a high speed stepper using SPI with Mesa cards
YMMV but not a lot
HTH
tomp
I tested Genes and my own kernel a lot over the last 2 days
There's not a lot of difference between them
I built mine from JT's instruction on Feb9 ( so had some newer pkgs than JT had )
I have different monitor than Gene
I have the npt fix from samco
see
and i force 600mhz AFTER booting ( not automated yet)
sudo sh -c "echo -n 600000 > /sys/devices/system/cpu/cpufreq/policy0/scaling_min_freq"
sudo sh -c "echo -n 600000 > /sys/devices/system/cpu/cpufreq/policy0/scaling_max_freq"
sudo sh -c "echo -n performance > /sys/devices/system/cpu/cpufreq/policy0/scaling_governor"
My system is responsive and videos smooth enough for me (infrequent blips i cant blame on anyone in particular)
here what you can expect:
run
latency-test period
then
IF you really beat on the system
like 4glxgears, 2 resized to larger
and chromium browser showing youtube video full screen, then back to default size so you can see the katency dialog
>I< get 106 usecs ( very long test )
IF you are nice to it ))
like 4 glxgears, no resizing, hands in pocketses
>I< get 50uS ( 13 hrs )
and here's some pix...
conclusion: MY OWN
iF you use it like a 1 bladed swiss army knif, you wont be developing and surfing and gaming
and you rely on the DRO ( not gui ) during cutting
THEN you can use a rpi3 or 4 to controll a slower stepp using gpio
a medium speed stepper using PiCNC
a high speed stepper using SPI with Mesa cards
YMMV but not a lot
HTH
tomp
Please Log in or Create an account to join the conversation.
Time to create page: 0.183 seconds