its just digits ! in real life your equipment can get only 5V + and low power quality - and its will be a problem !
WRITE procedure need every time more power than READ !
The drive is rated at 3.3V 0.9A, so shouldnāt draw more than 3W even at peak. Also, the corruption is sustained for the whole write cycle, not just at the start of the activity. I more suspect EMI arising from PCB layout rather than power supply issues, but Iām not enough of an electronics engineer to dig any further.
I did randomly try dropping the PCIe bus speed to 2.5 GT/s to see if that helped, but made no change to HDMI issue though did have the expected effect on throughput.
I spent excessive amounts of time failing to discover any way to change the framebuffer console HDMI resolution to see if that made a difference. The settings in /boot/env.txt seem to be ignored, as were any uboot variables I tried. I got as far as finding /sys/bus/platform/devices/soc/ff900000.vpu/drm/card0/card0-HDMI-A-1/edid (and /modes in same bit of the tree), but havenāt found anywhere in /sys that will let me write a new mode value to change the HDMI PHY.
Powering via the VIN port was vaguely on my todo list anyway to free up the USB-C port, but I donāt have the Molex crimp tool for building a cable. Is there a better alternative than buying the VIN-to-VIN cable, cutting the wires and soldering to a barrel connector?
Anyway, I think Iāve exhausted most of the effort I have for this, given I donāt actually intend to use HDMI in the day-to-day deployment. Thanks for your help, and hopefully this thread might be of some use to the next person to hit similar issues.
1 Like
I donāt know about EMF coming through the boards, as I think the M2X board does have copper layers that should hopefully absorb or deflect the incoming interferenceā¦
as for the VIN connector, I am afraid there is no other way to add a connector to itā¦
I too thank you for testing and cooperating in this problem hunting questā¦
good day !
Thanks for the info ! at the moment the question remains openā¦
That does remind me of one bit of information I donāt think I gave, which may be important if itās a hardware issue. The NVMe SSD is directly attached to the VIM3 board M.2 socket, not on an M2X board.
I am entirely sure about that part, as no one has reported a problem with thatā¦
As long as the SSD is flushly mounted with the port, it shouldnāt be a problemā¦
Is it placed at precisely exactly 90Ā° ?, perhaps loose connections are causing foul play here?
I even remember there was a user who created a case, where you could mount the SSD like thatā¦
1 Like
Thanks, Iām using a remix of that case that has a bit more ventilation ( https://www.thingiverse.com/thing:4269209 ). Yes, the SSD is mounted flush, at 90Ā° and held stable.
Also, board temperatures are hovering at around 30Ā°C idle/ 50Ā°C at load, so itās not a thermal issue. (I have the new style heatsink. No fan on the heatsink itself, but the board is held vertical in a steady airflow from an external fan.)
My mind is still boggled over your problemā¦
Have you tried other SSDs as well ?
No, Iām afraid that I havenāt got any spare NVMe SSDs to try. Theyāre still too modern for me to have decommissioned any!
As Iāve said twice now: The board is dead and Iām seeking RMA from Khadas ā¦ if I ever get a response.
Maybe you can send a personal message to them,
Katherine and Kenny should help you to do the RMA processā¦
ęä¹ē¢°å°äøę ·ēé®é¢ćęę²”ęäŗŗč§£å³äŗ ļ¼ pcie nvme å hdmi å½å大ę°ę®ęä½ nvmeę¶ hdmi č±å±é®é¢
For people reading this thread in attempts to find a solution there was a proposed solution from Khadas team members in another thread posted later and it is to add āpci=pcie_bus_perfā to the kernel cmdline in /boot/Env.txt.
Here is the link to the aforementioned thread:
https://forum.khadas.com/t/ubuntu-desktop-5-12-screen-flickering-issue-with-nvme/
1 Like