Fairly new setup and one of my drives in Cache went offline (2TB NVME) for the second time in two days. It has been running fine for a few months without any issues. I am moving the cache to RAID1 (was RAID0) but curious what could cause this. Running the lastest BIOS. 

 

Oct 18 12:31:53 Tower kernel: nvme nvme1: resetting controller due to AER
Oct 18 12:31:53 Tower kernel: nvme1n1: I/O Cmd(0x2) @ LBA 896841424, 680 blocks, I/O Error (sct 0x3 / sc 0x71) 
Oct 18 12:31:53 Tower kernel: I/O error, dev nvme1n1, sector 896841424 op 0x0:(READ) flags 0x80700 phys_seg 43 prio class 2
.......

Oct 18 12:31:53 Tower kernel: nvme nvme1: Removing after probe failure status: -19
Oct 18 12:31:53 Tower kernel: nvme1n1: detected capacity change from 3907029168 to 0
Oct 18 12:31:53 Tower kernel: BTRFS error (device nvme1n1p1): bdev /dev/nvme1n1p1 errs: wr 0, rd 1, flush 0, corrupt 0, gen 0 

tower-diagnostics-20231018-2028.zip

Edited October 18, 20232 yr by Dutchy74

I don't see any actual PCIe AER errors logged, but see if this helps:

 

https://forums.unraid.net/topic/118286-nvme-drives-throwing-errors-filling-logs-instantly-how-to-resolve/?do=findComment&comment=1165009

 

Thank you! Changed the settings and so far so good.