Samsung PM853T SSD dead?

Notice: Page may contain affiliate links for which we may earn a small commission through services like Amazon Affiliates or Skimlinks.

PnoT

Active Member
Mar 1, 2015
650
162
43
Texas
I recently had 8 drives in a ZFS enclosure and have since destroyed the pool and moved the SSDs out into other servers. One of the SSDs is showing a ZFS partition on it and only 930MB in size when it should be 960GB. I've tried to remove the zfs partition in gparted, cent OS, and windows to no avail.

Cent OS Live CD and gparted both show errors whenever the drive is being queried and the smart data looks corrupted via any OS that's trying to query it. The drive was put back into my other FreeNAS and it shows up but I can't wipe it as it's says "the operation is not permitted". I've also seen references of the drive being in use or locked.

I can report back with more detailed info tomorrow but wanted to see if anyone has run across this before.
 

PnoT

Active Member
Mar 1, 2015
650
162
43
Texas
Tried zeroing the drive?
I have tried through various methods and Live CDs , Gparted, and FreeNAS with no luck. Here's some information about what I'm seeing. The Smart DATA always shows "ERRORMOD" when trying to query it via various methods.

upload_2018-2-23_8-46-37.png

upload_2018-2-23_8-45-45.png
upload_2018-2-23_8-46-0.png

upload_2018-2-23_8-43-58.png

upload_2018-2-23_8-44-53.png

When trying to use dd there's no device it can attach to and run on. The drive doesn't show any labels, pools, or partitions on it in FreeNAS and trying to "wipe" the drive there results in "not permitted".
 

Attachments

wsuff

Member
Aug 16, 2015
75
13
8
If I remember right, FreeNAS keeps you from doing destructive things like wiping drives via kernel flag. Assuming you can still load this drive in a freenas machine & be detected, you should be able to sysctl kern.geom.debugflags=0x10 which then would allow dd to the device and u could follow that with UI based wipe.
 
Last edited:

JSchuricht

Active Member
Apr 4, 2011
198
74
28
I had a 480GB version with the same issue last year. It randomly dropped out of an array and while I was looking at the console disappeared then reappeared as a ~900MB drive. I went through most of what your trying and never found a solution to it.
 

PnoT

Active Member
Mar 1, 2015
650
162
43
Texas
If I remember right, FreeNAS keeps you from doing destructive things like wiping drives via kernel flag. Assuming you can still load this drive in a freenas machine & be detected, you should be able to sysctl kern.geom.debugflags=0x10 which then would allow dd to the device and u could follow that with UI based wipe.
So here's where I'm at so far after putting the drive in a FreeNAS 9.10 system in which it came out of.

Code:
[root@llwpfreenasp02] ~# sysctl kern.geom.debugflags=16
kern.geom.debugflags: 0 -> 16
[root@llwpfreenasp02] ~# dd if=/dev/zero of=/dev/da6 bs=512 count=1
dd: /dev/da6: Device not configured
1+0 records in
0+0 records out
0 bytes transferred in 0.000038 secs (0 bytes/sec)
If i use the command above, as you mentioned, and try it from the GUI it still spits out "Device not configured".

I also was trying to see if there were any partitions that FreeNAS could recognize

Code:
=>       34  125038525  da6  GPT  (60G)
         34       1024    1  bios-boot  (512K)
       1058          6       - free -  (3.0K)
       1064  125037488    2  freebsd-zfs  (60G)
  125038552          7       - free -  (3.5K)

=>      0  1965352  da2  (none)  (960M)
        0  1965352       - free -  (960M)
What's odd is the start of that drive is an absolute 0 and all of my other drives in the system are "34" but I"m not entirely sure what that means.

gpart info

Code:
[root@llwpfreenasp02] ~# gpart show da2
=>      0  1965352  da2  (none)  (960M)
        0  1965352       - free -  (960M)

[root@llwpfreenasp02] ~# gpart list da2
Geom name: da2
modified: true
state: OK
fwheads: 0
fwsectors: 0
last: 1965351
first: 0
entries: 0
scheme: (none)
Consumers:
1. Name: da2
   Mediasize: 1006260224 (960M)
   Sectorsize: 512
   Mode: r1w1e1
Here is the smartctl which looks bad because not all of the information is pulled and the firmware = "ERRORMOD"

Code:
[root@llwpfreenasp02] ~# smartctl -a /dev/da2
smartctl 6.5 2016-05-07 r4318 [FreeBSD 10.3-STABLE amd64] (local build)
Copyright (C) 2002-16, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF INFORMATION SECTION ===
Device Model:     MZ7GE960HMHP-000M3   00FN333 00FN336IBM
Serial Number:    90Y7I1ZK
LU WWN Device Id: 5 002538 800287cf5
Firmware Version: ERRORMOD
User Capacity:    1,006,260,224 bytes [1.00 GB]
Sector Size:      512 bytes logical/physical
Rotation Rate:    Solid State Device
Device is:        Not in smartctl database [for details use: -P showall]
ATA Version is:   ACS-2, ATA8-ACS T13/1699-D revision 4c
SATA Version is:  SATA 3.1, 6.0 Gb/s (current: 6.0 Gb/s)
Local Time is:    Fri Feb 23 20:50:06 2018 CST
SMART support is: Available - device has SMART capability.
SMART support is: Enabled

Read SMART Data failed: scsi error aborted command

=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED

Read SMART Log Directory failed: scsi error aborted command

Read SMART Error Log failed: scsi error aborted command

Read SMART Self-test Log failed: scsi error aborted command

Selective Self-tests/Logging not supported

I had a 480GB version with the same issue last year. It randomly dropped out of an array and while I was looking at the console disappeared then reappeared as a ~900MB drive. I went through most of what your trying and never found a solution to it.
It's been pretty frustrating for sure since the drive had maybe 10 hours on it tops and the other 7 that are from the same zpool are perfectly fine.
 
Last edited:

PnoT

Active Member
Mar 1, 2015
650
162
43
Texas
I still haven't been able to fix this drive so ordered another one in the meantime to move my project a long.
 

Miki

New Member
May 31, 2019
8
0
1
Have you since acquired any insights into how to extract the data from the drive?

I have experienced exactly this error - firmware version ERRORMOD and "nvme namespace" (= visible disk capacity) shown as 1GB - on a 3.84TB PM983 M.2 specifically model MZ1LB3T8HMLA-00007.