TheTick077

Well, I updated the BIOS, followed that thread's suggestions, changed port and cable on the offending drive. So let's hope that does it. If not, not sure what else to try. Thanks for the help/suggestions!

Thanks I'll read through that and give them a try. But my server isn't locking up, it is just getting those IRQ errors.

Thinking about it a little more, I have a couple of questions: it always is the same drive. Should I try a different port? Different SATA cable? Could either of those things possibly solve the issue?

Well that's not very helpful (not saying you aren't helpful - I understand there are situations outside of your control). I wish I had know this before I purchased my hardware and license. I don't see it mentioned anywhere that Ryzen boards aren't supported. So there is basically nothing I can do if my BIOS is up to date, and I'm on the Beta release? I'm just SOL and will have to rebuild my drive every ~10 days? Ok, just checked, and there is a new BIOS available for my mobo, but I'm honestly doubtful it will help at all right now. Should I still update it? https://www.gigabyte.com/us/Motherboard/B450-AORUS-ELITE-rev-10/support#support-dl-bios

Sorry! I rebooted the machine and reran the SMART test right before reading your post. So hopefully that didn't mess anything up. And I don't want to disable IOMMU since I use my windows VM as a "bare metal" daily driver and pass one of the video cards to it. tower-diagnostics-20200731-1313.zip

So I'm new to Unraid, and I built a system (AMD based B450 setup - if you need the details I can provide them). This is now the 3rd time I have had errors and a hard drive disabled. The first time I rebuilt and moved on after a clean SMART test. The 2nd I went to the Beta version of Unraid because I read that there were some issues with AMD boards that were resolved in the beta. Now this time, I am wondering if there is something else going on... I saved off the logs from the last two times, but here is what I think are where things begin to get screwy (Full logs also attached): Jul 19 10:18:42 Tower kernel: ahci 0000:01:00.1: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x00000000d37ee000 flags=0x0000] Jul 19 10:18:42 Tower kernel: ata6.00: exception Emask 0x10 SAct 0xffe000 SErr 0x0 action 0x6 frozen Jul 19 10:18:42 Tower kernel: ata6.00: irq_stat 0x08000000, interface fatal error Jul 19 10:18:42 Tower kernel: ata6.00: failed command: WRITE FPDMA QUEUED Jul 19 10:18:42 Tower kernel: ata6.00: cmd 61/08:68:c0:e1:bf/00:00:00:00:00/40 tag 13 ncq dma 4096 out Jul 19 10:18:42 Tower kernel: res 40/00:b8:f0:b6:9f/00:00:02:00:00/40 Emask 0x10 (ATA bus error) Jul 19 10:18:42 Tower kernel: ata6.00: status: { DRDY } And then something similar today: Jul 30 14:05:54 Tower kernel: ahci 0000:01:00.1: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x000e address=0xfecfe000 flags=0x0000] Jul 30 14:05:54 Tower kernel: ata6.00: exception Emask 0x10 SAct 0x1ffff0 SErr 0x0 action 0x6 frozen Jul 30 14:05:54 Tower kernel: ata6.00: irq_stat 0x08000000, interface fatal error Jul 30 14:05:54 Tower kernel: ata6.00: failed command: WRITE FPDMA QUEUED Jul 30 14:05:54 Tower kernel: ata6.00: cmd 61/08:20:60:ae:5f/00:00:00:00:00/40 tag 4 ncq dma 4096 out Jul 30 14:05:54 Tower kernel: res 40/00:40:b8:78:65/00:00:00:00:00/40 Emask 0x10 (ATA bus error) Jul 30 14:05:54 Tower kernel: ata6.00: status: { DRDY } Is my hardware failing? Is there something else going on? Not sure what I need to do, but I can't have this drive fail every 10 days... tower-syslog-20200731-1645.zip tower-syslog-20200720-1401.zip