I have a zfs pool made of 4 1tb SSDs. Qty1 Crucial MX500 1TB 3D NAND SATA 2.5-inch and Qty3 Samsung SSD 870 EVO 1TB.

I received notification that the life expectancy of the Crucial SSD was at 00% a few weeks ago. I have been super busy, and i didn't get around to checking on the pool until tonight.

Below is what I see when I check the pool's status. I'm kinda freaked out. We use ZFS at work, but it is REALLY rare for us to see any errors. And when we do get errors, we clear them once. when they come back the drive gets replaced. This cache has only been in the server for about 18 months.

Any thoughts / suggestions re: what I should do would be greatly appreciated. I added cache because my VMs seemed really slow, but frankly the cache hasn't seemed to have helped that at all. Might it be possible / reasonable to just migrate everything off the cache to spinny disks and chuck the cache entirely? :(

root@unraid:/dev# zpool status
pool: cache
 state: ONLINE
status: One or more devices has experienced an unrecoverable error.  An
        attempt was made to correct the error.  Applications are unaffected.
action: Determine if the device needs to be replaced, and clear the errors
        using 'zpool clear' or replace the device with 'zpool replace'.
   see: https://openzfs.github.io/openzfs-docs/msg/ZFS-8000-9P
config:

        NAME        STATE     READ WRITE CKSUM
        cache       ONLINE       0     0     0
          raidz2-0  ONLINE       0     0     0
            sdaf1   ONLINE       0    38     0
            sdz1    ONLINE      10    61     0
            sdn1    ONLINE      13   121     0
            sdt1    ONLINE       0    76     0

errors: No known data errors

Please post the diagnostics.

Diagnostics attached. :) Thanks!

unraid-diagnostics-20250919-2121.zip

Logs are being spammed with SMB related errors, and the pool errors are not visible, but unlikely that it's a device problem, I would recommend connecting the 4 SSDs to the onboard SATA controller, using new cables and retesting, and alto try to fix the SMB spam issue.