JorgeB

Please post the diagnostics

I don't see anything logged on the Unraid side, suggesting an external issue.

There are some ATA issues logged, but that doesn't explain a crash. Since you are using a Ryzen CPU, make sure this has been taken care of: https://forums.unraid.net/topic/46802-faq-for-unraid-v6/page/2/#findComment-819173

Don't see anything that would justify a crash, and since you were still able to get the diags, the server was not really crashed, I do see a lot of these: Jun 5 17:10:17 HADES nginx: 2026/06/05 17:10:17 [error] 11342#11342: *153975 upstream timed out (110: Connection timed out) while reading response header from upstream, client: 10.0.0.74, server: hash.myunraid.net, request: "GET /plugins/dwmemtester/include/dwmemtester_status.php?getfs=no HTTP/2.0", subrequest: "/auth-request.php", upstream: "fastcgi://unix:/var/run/php-fpm.sock", host: "hash.myunraid.net:446", referrer: Suggesting an issue with that plugin, possibly could make the GUI stop responding; you can try booting in safe mode.

Considering the errors and multiplied risks, there is no point in continuing.

Check/replace all connections; try to avoid splitters as much as possible, but make sure you are not splitting a SATA port into more than two. Molex can handle more than two, though still not recommended.

Don't see obvious issues, but any particular reason you are using NTFS for the dockercache pool? NTFS support is limited with Linux; recommend backing up and recreating that pool with a Linux filesystem.

You can enable the syslog server and post that if it crashes again.

Syslog shows errors with multiple disks, are you using any kind of power splitters?

You can use the toggle with 7.3.x, then reboot

The server should not crash just by dealing with an emulated disk. Diags show the disk dropping offline before; this is typically a power/connection issue. Check/replace cables for disk5 and post new diags after array start (the disk will still be disabled; this is expected)

Diags look good so far, no issues that I can see, and thanks for the donation! Much appreciated.

Settings - Boot Parameters, then add that option to the boot option you are using.

Rebuild finished a couple of days ago: Jun 5 16:42:30 HADES kernel: md: sync done. time=14045sec Jun 5 16:42:30 HADES kernel: md: recovery thread: exit status: 0

There are some PCI related corrected errors spamming the log, add the option below then start a new syslog and post that if it hapens again. https://forums.unraid.net/topic/118286-nvme-drives-throwing-errors-filling-logs-instantly-how-to-resolve/?do=findComment&comment=1165009

And never split one SATA port into more than two.

I assume these are the pool members? And they are all from the same pool? /dev/nvme0n1p1: UUID="299134d5-d2d5-41d9-9bfa-3e98d1e3f1d5" TYPE="crypto_LUKS" PARTUUID="e414749a-01" /dev/nvme2n1p1: UUID="8416d39f-e189-42e1-a1b8-956a23215ce8" TYPE="crypto_LUKS" PARTUUID="b660afb9-01" /dev/nvme3n1p1: UUID="2d3fcb77-83de-48a1-b4c2-11d4fe5ba331" TYPE="crypto_LUKS" PARTUUID="0262e045-35e3-48a5-8af5-47f862bab439" /dev/nvme4n1p1: UUID="b2d6b8d5-d4db-4938-a66b-907cd3ffa1ee" TYPE="crypto_LUKS" PARTUUID="d8fe2adb-7f6b-4fbc-9866-3daf82e56b31" If yes, on main, create a new pool with the name you like and 4 slots assign the pool devices, leave the filesystem set to auto It should ask for the encryption key/passphrase, then start the array to import the pool If it fails to mount, post the diags with the array started

The server is running out of RAM, you have a rogue process (starter.sh) using approximately 61GB That is likely running inside a container.

There are multiple disks dropping across different controllers, suggesting more of a power issue; it could be the PSU itself, or if there are any splitters being used, it could also be related to that

Just did a test and it's not possible. With RAIDZ vdevs in the pool, the zpool remove command is completely blocked, so even after adding a new vdev to special or dedup, it still doesn't allow you to remove the other one, since the new devices are smaller, and you cannot also do a replacement. I'm afraid the only way would be to back up and recreate the pool.

Yep, 8 mirrored vdevs. Should resume; it can go back just a little, but it should not restart. This is the scanned metadata, and the value should keep increasing as the resilver progresses, and it typically reaches the full capacity (1 TB in this case) before the pool is fully resilvered.

I don't see any relevant logged; post a new syslog after the next crash, and mention the aprox. crash timecode, together with the diags mostly to see the hardware.

Click the link If that fails, see if you can get the syslog cp /var/log/syslog /boot/syslog.txt

You can use the steps here: https://forums.unraid.net/topic/46802-faq-for-unraid-v6/#findComment-511923