I think there is some sort of hardware issue, but I can't figure out what. Any help is greatly appreciated. This crash happens a couple times a week. Previously notices a corruption in the docker image, and I fixed this. Now the issue seems like it might be above me head.

marmalade-diagnostics-20250713-2247.zip

Enable the syslog server and post that after a crash.

Update on this!

Did some investigating and found a bent socket pin on one of the two cpu sockets. Sent it out to get repaired yesterday and got her back online.
Unfortunately, this has not solved our issue. After about 16 hours of uptime, the server stalled and had to be power cycled.

As requested: Here are updated diagnostics and syslogs. Granted, the unraid server seems to have not been connected to the syslog server for the aforementioned 16 hours of uptime. But it does contain syslogs from previous crashes. I anticipate on updating this post with more syslogs within 24 hours🤦

The configuration is 2x Intel Xeon E5-2690 v4 with 256 GB ECC memory and an Nvidia Quadro RTX 6000. Storage is connected via a SAS controller running to a JBOD.

Your help is greatly appreciated,
big_chuz

marmalade (2).zip

Edited August 15, 2025Aug 15 by big_chuz

Lots of corruption errors on the Docker image and also multiple segfaults, that's typicall RAM, but should not happen with ECC. Try re-creating the Docker image, then use the server with half the RAM. If more corruptions are detected, recreate it again and try the other half.

https://docs.unraid.net/unraid-os/manual/docker-management/#re-create-the-docker-image-file

Then:

https://docs.unraid.net/unraid-os/manual/docker-management/#re-installing-docker-applications

Also see below if you have any custom docker networks:

https://docs.unraid.net/unraid-os/manual/docker-management/#docker-custom-networks

Trying this at some point today, but the server crashed again while I was asleep and I wanted to push the logs

Marmalade (2).zip