Can't sleep, so I am back on it.
Firmware Revision: ERRORMOD smartctl -a /dev/nvme3smartctl 7.5 2025-04-30 r5714 [FreeBSD 14.3-RELEASE-p5 amd64] (local build)
Copyright (C) 2002-25, Bruce Allen, Christian Franke, www.smartmontools.org
=== START OF INFORMATION SECTION ===
Model Number: SAMSUNG MZ1LB1T9HALS-00007
Serial Number: S436NA0N715552
Firmware Version: ERRORMOD
PCI Vendor/Subsystem ID: 0x144d
IEEE OUI Identifier: 0x002538
Total NVM Capacity: 1,920,383,410,176 [1.92 TB]
Unallocated NVM Capacity: 0
Controller ID: 4
NVMe Version: 1.2
Number of Namespaces: 1
Namespace 1 Size/Capacity: 1,073,741,824 [1.07 GB]
Namespace 1 Formatted LBA Size: 512
Local Time is: Mon Nov 3 00:13:11 2025 +07
Firmware Updates (0x17): 3 Slots, Slot 1 R/O, no Reset required
Optional Admin Commands (0x000f): Security Format Frmw_DL NS_Mngmt
Optional NVM Commands (0x001f): Comp Wr_Unc DS_Mngmt Wr_Zero Sav/Sel_Feat
Log Page Attributes (0x03): S/H_per_NS Cmd_Eff_Lg
Maximum Data Transfer Size: 512 Pages
Warning Comp. Temp. Threshold: 86 Celsius
Critical Comp. Temp. Threshold: 87 Celsius
Namespace 1 Features (0x02): NA_Fields
Supported Power States
St Op Max Active Idle RL RT WL WT Ent_Lat Ex_Lat
0 + 8.00W - - 0 0 0 0 0 0
Supported LBA Sizes (NSID 0x1)
Id Fmt Data Metadt Rel_Perf
0 + 512 0 0
1 - 4096 0 0
=== START OF SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED
SMART/Health Information (NVMe Log 0x02, NSID 0xffffffff)
Critical Warning: 0x00
Temperature: -
Available Spare: 0%
Available Spare Threshold: 10%
Percentage Used: 255%
Data Units Read: 0
Data Units Written: 0
Host Read Commands: 0
Host Write Commands: 0
Controller Busy Time: 0
Power Cycles: 0
Power On Hours: 0
Unsafe Shutdowns: 0
Media and Data Integrity Errors: 0
Error Information Log Entries: 0
Warning Comp. Temperature Time: 0
Critical Comp. Temperature Time: 0
Error Information (NVMe Log 0x01, 16 of 64 entries)
No Errors Logged
Self-tests not supporteddo not do this. every time we hear about someone doing this, we hear about them losing data to mysterious failures. next time, put partition tables on your disks.
Yes, I might well use partitions next time.
Yes, there is a fair amount on searching.
Is there a reason for it? Do you have any pointers? I have a pool like that which would be a bit hard for me to backup and restore.
It seems some SSD manufacturers are automatically using space left out of reserved partitions for wear leveling and overprovisionning.
it is probably not related to the OP's drive failures, but we've heard of people's BIOSes stomping on disks with no partition table accidentally. arguably buggy bios, but really, just best to have the structure there. plus, yes, some SSDs make assumptions centering around a normal-style partition layout. all in all, we don't see any argument for using "dangerously dedicated" disks like this, it's not like the partition table takes up oodles of space.
How would I update firmware with camcontrol? Especially when the firmware to update is part of the Samsung program.
Understood.
Maybe a Windows VM on Bhyve would do it with PCI passthrough to the VM. I didn't try it with a disk drive but a USB controller. The VM can see the drive after the passthrough. To be able to passthrough it to the VM, it should be fully detached software wise from the host, see devctl manpage for detaching and attaching the pci device on the fly.
doh. you're correct, of course. NVME not being SCSI underneath is probably gonna trip us up personally for a while (we have the SCSI diamond as a tattoo)
There are multiple reasons. One was already mentioned: Other parties (like the BIOS, or other operating systems) may see a disk without any partitions, assume that it is a blank disk, and put a partition table on it as a safety measure. Similarly, if one has an invalid partition on the disk (for example the GPT backup at the end of the disk missing), a "helpful" BIOS might automatically "fix" it. From their viewpoint, that seemed like a good idea. I used to work on very large storage systems (with thousands of disks), and we would regularly find empty disks overwritten with either Windows images, or Reiser file systems (for some reason, there was a Linux distro that liked to use Reiser, which also murders your wife, old cruel joke).
Maybe. Worth trying. Usually, these software are also available for DOS, and it is easy to set up a temporary bootable DOS USB stick (I used to use FreeDOS for it).
It might work, but more likely it will not. While theoretically there are both SCSI and SATA protocols for firmware updating, in practice firmware modification tends to be highly vendor specific, for safety reasons. Disk vendors hate it when hackers put nasty firmware on their drives, so the way to update disk firmware tends to be pretty secure and quite undocumented, unless you get the instructions under NDA from the manufacturer. But there is no harm in trying camcontrol or nvmecontrol at this point.
our experience is that hard drives from 2010-ish onwards quietly switched to signed updates, and but also their update utilities really are/always have been just glitzified wrappers around the official SCSI/NVMe commands, and the hard part is finding the right file to feed to
camcontrol (or nvmecontrol respectively). them switching to signed updates actually made it easier to find the files floating around.
