JorgeB

Please post the diagnostics.

Parity was already disabled at last boot, so diags don't show what happened, there are recent CRC errors so replace the SATA cable and re-sync parity. P.S. Lots of call traces on the log, see if updating to v6.10 gets rid of those.

Jul 24 13:18:49 Nexus kernel: sd 10:0:0:0: [sdc] Synchronizing SCSI cache Jul 24 13:18:49 Nexus kernel: sd 10:0:0:0: [sdc] Synchronize Cache(10) failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK Jul 24 13:18:49 Nexus kernel: sd 10:0:1:0: [sdd] Synchronizing SCSI cache Jul 24 13:18:49 Nexus kernel: sd 10:0:1:0: [sdd] Synchronize Cache(10) failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK Jul 24 13:18:49 Nexus kernel: sd 10:0:2:0: [sde] Synchronizing SCSI cache Jul 24 13:18:49 Nexus kernel: sd 10:0:2:0: [sde] Synchronize Cache(10) failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK Jul 24 13:18:49 Nexus kernel: sd 10:0:3:0: [sdf] Synchronizing SCSI cache Jul 24 13:18:49 Nexus kernel: sd 10:0:3:0: [sdf] Synchronize Cache(10) failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK Jul 24 13:18:49 Nexus kernel: sd 10:0:4:0: [sdg] Synchronizing SCSI cache Jul 24 13:18:49 Nexus kernel: sd 10:0:4:0: [sdg] Synchronize Cache(10) failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK Jul 24 13:18:49 Nexus kernel: sd 10:0:5:0: [sdh] Synchronizing SCSI cache Jul 24 13:18:49 Nexus kernel: sd 10:0:5:0: [sdh] Synchronize Cache(10) failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK Multiple disks dropped at the same time, this suggests a power/connection problem, could also be an issue with the HBA, though much less likely.

Run a scrub, then check that in the output all errors were corrected.

Nothing obvious, try connecting directly to a router just for testing.

Best bet is posting in the existing Nvidia plugin support thread:

Best bet is to ask for help in the docker support forum/discord, assuming there's one:

It's logged as a disk problem, at least on SMART, but the extended test passed, and theses errors can be intermittent some times, I would suggest swapping cables/slot with a different disk to rule that out then try again, then grab diags before rebooting if it happens again.

Best bet is to post in the existing Nvidia plugin support thread: https://forums.unraid.net/topic/98978-plugin-nvidia-driver/

Please post the diagnostics after a crash.

Assuming you're on v6.10:

ATA errors are gone so far, some GPU related log spam, not sure what that's about though, but if all is working normally possibly OK to ignore.

Those will be gone once the disk is cleared/formatted.

Enable the syslog server and post that after a crash.

There's nothing relevant in the log posted, that usually indicates a hardware problem.

This device is being pass-trough to the Windows VM: <hostdev mode='subsystem' type='pci' managed='yes'> <driver name='vfio'/> <source> <address domain='0x0000' bus='0x06' slot='0x00' function='0x0'/> </source> And it is the NIC: 06:00.0 Ethernet controller [0200]: Intel Corporation Ethernet Controller I225-V [8086:15f3] (rev 03) Subsystem: Micro-Star International Co., Ltd. [MSI] Ethernet Controller I225-V [1462:7d32] When you change/add/remove hardware it's normal for some devices to change address, so you might need to adjust.

The storage part is usually plug and play, VMs might need some adjusting, i.e., core assignments and hardware pass-through if you're doing it.

Do you known the time this happened? Can't find any issues with libvirt in the posted log.

That's the link speed from the HBA to the expander, 8x600MB/s with dual link, and the max theoretical speed possible, you can get better than that with a SAS3 HBA+Expander, I got around 5500MB/s total with the 9300-8i and Intel RES3TV360, because they are SATA devices they will never reach quite max PCIe 3.0 device, for that you'd need SAS3 devices, still good speed for 24 devices, and note that in this case, unlike with a SAS2 HBA + expander, speed might vary with the devices used, can only speak for the devices I used to test, unless you buy SAS3 disks.

Sorry for the late reply, was away for a week, if he still needs help please ask the user to post the diags after array start, and please ping me if he does since I don't usually check this subforum.

Swap disk4 cables (both power and SATA) with a different disk, then see if the problem follows the disk or not.

parent transid verify failed on 180224 wanted 4989515 found 4989510 This error is fatal with btrfs, it means some writes were lost due to write barriers not being respected, most times a controller/device firmware issue, you'll need to re-format but can try the btrfs restore option here, though it doesn't always work 100% with this error.

Don't see how, if you can get them to boot, try another PC if available, delete the BIOS, it's not needed for Unraid and makes booting faster and it will prevent the issues that can happen with with some boards/BIOS.

Probably can only solve that by rebooting.

Check filesystem on disk 3