[0x08000800]: an uncorrected error caused a data fabric sync flood event

J

Jerome69

New Member
Apr 5, 2026
6
0
1
Hello everybody,

First of all, sorry for my english, I'm French :)

I have a mini forum UM690 Pro (AMD Ryzen 9 6900HX, 32Gb DDR5,AMD Radeon 680M), but since 2 weeks, It reboots many times per day (sometimes 10 per hour).

The first think I did was changing the CPU thermal paste (on the BIOS, the temperature was about 60°, 38° after changing).
But it didn't solved the problem.

I tried to reinstall the lastest proxmox version, changed the kernel version (6.2.16-20) and today I reinstalled the 8.4 Proxmox version.
After 30 minutes, the computer reboots.

I have tested the RAM with Memtest and it passed.
The tests was launched at 9:00PM and at 7:00AM the computer still worked.

On Proxmox, I tried to install the only VM I need to have internet : pfSense. So the CPU is not really stressed.

I have changed the power supply, but maybe it was a cheap one, and it does't resolved my problem.

I tried to disable IOMMU on the grub (I can't do it into the BIOS) and the c-state.

Does someone has encountered this problem, and solved it ?

Thanks in advance.
 
Hi Dominik,

Thank you for your help.

I tried to install Windows 11, but I have the same problems.

After contacting Minis Forum, it's a hardware problem.

Thanks for your time :)
 
Jerome69 said:
Hi Dominik,

Thank you for your help.

I tried to install Windows 11, but I have the same problems.

After contacting Minis Forum, it's a hardware problem.

Thanks for your time :)
Click to expand...
Hi, Jerome69, I/m using a mini forum ms-a2 with AMD R99950HX with a dGPU 4070LP. I'm facing same problem witch pve/windows always crash after some gpu usage.
Logs shown the same "data fabric sync flood".
How do you solved your problem? With hardware repair or bios update?

THX.
 
zzjin said:
Hi, Jerome69, I/m using a mini forum ms-a2 with AMD R99950HX with a dGPU 4070LP. I'm facing same problem witch pve/windows always crash after some gpu usage.
Logs shown the same "data fabric sync flood".
How do you solved your problem? With hardware repair or bios update?

THX.
Click to expand...
Hi zzjin,
I didn't solved the problem for the moment, but it seems that's a hardware problem.
Minisforum offer me a repair service, I don't have an order number (bought on Leboncoin).
Did you see the CPU temperature on the BIOS ?
 
I solved this issue with kernel parameters:
Code: 
processor.max_cstate=1

apparently this problem started with PVE kernel update (not sure which one, probably latest as I have never had this problem before)

my machine:
UM790 Pro Ryzen 9 7940HS
16 x AMD Ryzen 9 7940HS w/ Radeon 780M Graphics (1 Socket)
 
Last edited:
I tryied this, but it didn't work for me. But I'm not a specialist, so mabye I didn't used correctly the parameter...
But even on Windows I have the reboot, so I thought that's not a software problem...
 
did you verify it works:
Code: 
cat /proc/cmdline

BOOT_IMAGE=/vmlinuz-6.17.13-2-pve root=ZFS=/ROOT/pve-1 ro root=ZFS=rpool/ROOT/pve-1 boot=zfs processor.max_cstate=1
 
I added the information on the kernel with this line :
Code: 
GRUB_CMDLINE_LINUX_DEFAULT="quiet idle=nomwait processor.max_cstate=1"
And for me it works, I was able to see this line on the logs with no error.

But if the reboots occured with Windows, I can therforce deduce that it's a hardware probleme, no ?
 
Jerome69 said:
Hi zzjin,
I didn't solved the problem for the moment, but it seems that's a hardware problem.
Minisforum offer me a repair service, I don't have an order number (bought on Leboncoin).
Did you see the CPU temperature on the BIOS ?
Click to expand...
In my case, Windows crashes just a few minutes after startup, before the temperature even rises.
 
Before replacing the CPU thermal paste, temperature was 60°C in the BIOS, 38°C after changing.
So maybe the temperature is rising more than you think :)
 
You must log in or register to reply here.
Top Bottom
Back