HonestLiar

Thanks for the reply. I had seen that and forgot to put it in the original message. I have already disabled C-States and made sure my RAM was at one of the supported speeds. But re-reading it occurred to me that I should BIOS update as well. While I was already doing that I changed like 6 other things.... I replaced the PSU with 1000w one. I reseated RAM. I unplugged and replugged all drives. I reapplied electrical tape to my shucked 3.3v SATA pins. (this might have actually been an issue since when I was looking at it, the existing tape was mangled) I ran memtest for 48 hours with no issues. After all that, I've been up for 2-3 days no with no issue. Of course, this has happened in the past where I'd get a week of good stuff and then more crashes but only time will tell I guess.

Been having near constant periodic crashes. The thing will sometimes stay on for the whole week, sometimes just for a few hours. Been like this for a month or two now. I have made sure to switch my docker containers to ipvlan. Downgrading back to 6.11.5 did not solve the issue. I have the syslog from the most recent crash, but I'm not sure what I'm looking for. I have attached the syslog and diagnostics file. Some other maybe related notes. I have a drive with SMART errors, but it's not in the array. When the thing is on, there are no other issues I can see. Maybe this is a PSU issue? I was reusing a 750w PSU so maybe it can't handle the rest? (5800x/3080) The server used to be my gaming PC but I didn't use it much so I converted it. The PC had no issues while I was using it for gaming. When it does crash, I am unable to turn it back on via the power button. Need to shut off power completely, then turn it back on via the power button. syslog mainstorage-diagnostics-20230819-1917.zip