Proxmox restart

[cgarbero]

Hello i have a problem with proxmox, recently i install proxmox the last version 9 on a HP DL20 gen 11 Server . and when i am preparing the vm , proxmox restart. I create RAID ZFS 1. Here i post some errors that i was seeing. I update the server firmware with the SPP of HPE proliant gen 11. I dont have problem with the server only when i am using proxmox creating a vm or doing some configuration the proxmox server crash. Help me please

DL20 Gen11 Specification
32GB RAM
Intel(R) Xeon(R) E E-2434
2 disk vK000480GXNZA

root@Server2:~# journalctl -b -1 | less Oct 07 07:40:14 Server2 kernel: Linux version 6.14.8-2-pve (build@proxmox) (gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44) #1 SMP PREEMPT_DYNAMIC PMX 6.14.8-2 (2025-07-22T10:04Z) ()
Oct 07 07:40:14 Server2 kernel: Command line: initrd=\EFI\proxmox\6.14.8-2-pve\initrd.img-6.14.8-2-pve root=ZFS=rpool/ROOT/pve-1 boot=zfs split_lock_detect=warn
Oct 07 07:40:14 Server2 kernel: KERNEL supported cpus:
Oct 07 07:40:14 Server2 kernel: Intel GenuineIntel
Oct 07 07:40:14 Server2 kernel: AMD AuthenticAMD
Oct 07 07:40:14 Server2 kernel: Hygon HygonGenuine
Oct 07 07:40:14 Server2 kernel: Centaur CentaurHauls
Oct 07 07:40:14 Server2 kernel: zhaoxin Shanghai
Oct 07 07:40:14 Server2 kernel: x86/tme: not enabled by BIOS
Oct 07 07:40:14 Server2 kernel: x86/split lock detection: #AC: crashing the kernel on kernel split_locks and warning on user-space split_locks
Oct 07 07:40:14 Server2 kernel: BIOS-provided physical RAM map:
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x0000000000000000-0x000000000009ffff] usable
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x00000000000a0000-0x00000000000fffff] reserved
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x0000000000100000-0x000000006bad9fff] usable
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x000000006bada000-0x000000006baddfff] reserved
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x000000006bade000-0x00000000710e0fff] usable
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x00000000710e1000-0x00000000714e0fff] ACPI NVS
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x00000000714e1000-0x0000000072271fff] usable
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x0000000072272000-0x0000000072272fff] reserved
Oct 07 07:40:14 Server2 kernel: BIOS-e820: [mem 0x0000000072273000-0x000000007242cfff] usable
:
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

root@Server2:~# dmesg -T | grep -iE "error|fail|warn" [Tue Oct 7 08:41:37 2025] Command line: initrd=\EFI\proxmox\6.14.8-2-pve\initrd.img-6.14.8-2-pve root=ZFS=rpool/ROOT/pve-1 boot=zfs split_lock_detect=warn
[Tue Oct 7 08:41:37 2025] x86/split lock detection: #AC: crashing the kernel on kernel split_locks and warning on user-space split_locks
[Tue Oct 7 08:41:37 2025] Warning: node 0 [mem 0x00001000-0x7eafffff] overlaps with itself [mem 0x00100000-0x6676efff]
[Tue Oct 7 08:41:37 2025] Kernel command line: initrd=\EFI\proxmox\6.14.8-2-pve\initrd.img-6.14.8-2-pve root=ZFS=rpool/ROOT/pve-1 boot=zfs split_lock_detect=warn
[Tue Oct 7 08:41:37 2025] Unknown kernel command line parameters "boot=zfs split_lock_detect=warn", will be passed to user space.
[Tue Oct 7 08:41:37 2025] ERST: Error Record Serialization Table (ERST) support is initialized.
[Tue Oct 7 08:41:38 2025] i8042 i8042: probe with driver i8042 failed with error -5
[Tue Oct 7 08:41:39 2025] RAS: Correctable Errors collector initialized.
[Tue Oct 7 08:41:39 2025] split_lock_detect=warn

 

[Onslow]

Are there any power-saving features enabled in the hardware setup? If yes, try disabling them. This is usually recommended.
For instance I have found a report of similar issue which was caused most likely by ASPM [0].

I don't know if it can be disabled in the setup. If not, try to disable it in the working system.

[0] https://www.truenas.com/community/t...and-warning-on-user-space-split_locks.114282/

Other reason I've found is some graphics driver, e.g. Nvidia.

Though I'm only guessing.