Hi, hope everyone is keeping well.

I'm in the process of converting my single 970_EVO_1TB XFS cache drive to ZFS and then adding another 1TB as RAID 1 mirror. I've followed spaceinvader's tutorial (https://www.youtube.com/watch?v=vXF8au5o9Tw) where cache is backed up to the array using mover. However, halfway through the process mover just stopped and there's still data on the cache. When restarting mover nothing happens!

Entries in the syslog

Tower move: mover: started

Tower kernel: nvme2n1: I/O Cmd(0x2) @ LBA 1533967328, 256 blocks, I/O Error (sct 0x2 / sc 0x81) MORE

Tower kernel: critical medium error, dev nvme2n1, sector 1533967328 op 0x0:(READ) flags 0x80700 phys_seg 1 prio class 0

Tower kernel: nvme2n1: I/O Cmd(0x2) @ LBA 1533967328, 256 blocks, I/O Error (sct 0x2 / sc 0x81) MORE DNR

Tower kernel: critical medium error, dev nvme2n1, sector 1533967328 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 0

Tower kernel: nvme2n1: I/O Cmd(0x2) @ LBA 1533967328, 256 blocks, I/O Error (sct 0x2 / sc 0x81) MORE DNR

Tower kernel: critical medium error, dev nvme2n1, sector 1533967328 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 0

SMART

=== START OF SMART DATA SECTION ===

SMART overall-health self-assessment test result: PASSED

SMART/Health Information (NVMe Log 0x02)

Critical Warning: 0x00

Temperature: 32 Celsius

Available Spare: 98%

Available Spare Threshold: 10%

Percentage Used: 0%

Data Units Read: 69,926,739 [35.8 TB]

Data Units Written: 63,703,789 [32.6 TB]

Host Read Commands: 598,075,028

Host Write Commands: 1,593,565,091

Controller Busy Time: 20,038

Power Cycles: 80

Power On Hours: 8,004

Unsafe Shutdowns: 41

Media and Data Integrity Errors: 686

Error Information Log Entries: 766

Warning Comp. Temperature Time: 0

Critical Comp. Temperature Time: 0

Temperature Sensor 1: 32 Celsius

Temperature Sensor 2: 40 Celsius

Error Information (NVMe Log 0x01, 16 of 64 entries)

Num ErrCount SQId CmdId Status PELoc LBA NSID VS Message

0 766 0 0xd006 0x4004 - 0 0 - Invalid Field in Command

Self-test Log (NVMe Log 0x06)

Self-test status: No self-test in progress

Num Test_Description Status Power_on_Hours Failing_LBA NSID Seg SCT Code

0 Short Completed: failed segments 7997 19867936 1 7 - -

1 Extended Completed: failed segments 7997 20803392 1 7 - -

2 Short Completed: failed segments 7997 19867936 1 7 - -

Any way to rectify this issue or has the SSD completely failed?

Edited October 10, 2025Oct 10 by unraid20

Extended tests are failing, so the device should be replaced.

2 minutes ago, JorgeB said:

Extended tests are failing, so the device should be replaced.

Thank you. If I replace it with the new 1TB SSD drive, format in ZFS and then reverse mover from cache to array on the shares will all my data be in tact?

Edited October 10, 2025Oct 10 by unraid20

Possibly not all the data was copied, but if it was, you should be OK.

1 hour ago, JorgeB said:

Possibly not all the data was copied, but if it was, you should be OK.

There still appears to be appdata on the failed cache drive. Safer to copy to the new SSD from a backup in this case?

Edited October 10, 2025Oct 10 by unraid20

Possibly, as long as it's a good and recent backup.

On 10/10/2025 at 10:22 PM, JorgeB said:

Possibly, as long as it's a good and recent backup.

I've resolved this now with a recent backup. Much appreciated thank you.

Also on one of my 3.5" HDD array disks I have the error below even though the Last SMART test result: Completed without error

Anything I ought to do regarding this?

199

UDMA CRC error count

0x0032

200

200

000

Old age

Always

Never

8

That's typically caused by a bad SATA cable, if the attribute keeps increasing, replace it, if not, they could be old errors.