Problem DEC750 freeze with 26.7 version

[droumanet]

After few days running, my DEC750 freeze.
Console port says something about
zfs: WARNING: Pool 'zroot' has encoutered an uncorrectable I/O failure and has been suspended

AI help me to check temperature was too high, so I changed place and now it seems to be ok (according to os-smart: max 68°C)

Anybody have an idea how to troubleshoot (console is not usable) ?

[Patrick M. Hausen]

Your SSD might be failing. Run a long SMART test. Also run a zpool scrub.

[droumanet]

I did many tests and there is no failure. AI suspected too much write on it, then I reduced rules log, rddtools and some settings.
Let see for next tests

[pfry]

[...]AI suspected too much write on it[...]

"Services: SMART" -> "Info", "Info type" = "Attributes", "View". Anything out of nominal? I have most rule logging enabled, and show 2.3TB written over nearly two years.

[droumanet]

It seems I've 12 TB in less than one year. Main of them are Outbound DNS level 3 (down to level 2).
This morning, here are statistics:

=== START OF SMART DATA SECTION ===
SMART/Health Information (NVMe Log 0x02, NSID 0xffffffff)
Critical Warning:                   0x00
Temperature:                        52 Celsius
Available Spare:                    100%
Available Spare Threshold:          10%
Percentage Used:                    13%
Data Units Read:                    662,615 [339 GB]
Data Units Written:                 24,519,123 [12.5 TB]
Host Read Commands:                 4,037,958
Host Write Commands:                465,833,667
Controller Busy Time:               4,513,538
Power Cycles:                       30
Power On Hours:                     4,677
Unsafe Shutdowns:                   24
Media and Data Integrity Errors:    0
Error Information Log Entries:      0
Warning  Comp. Temperature Time:    0
Critical Comp. Temperature Time:    0
Temperature Sensor 1:               66 Celsius
Temperature Sensor 2:               41 Celsius
Temperature Sensor 3:               52 Celsius
Thermal Temp. 1 Transition Count:   93
Thermal Temp. 1 Total Time:         4478

The main temperature of the firewall (in Dashboard) is 39.1°C, so 66°C for NVMe0 is strange, no?

[Patrick M. Hausen]

Passively cooled 66 C is not uncommon. Percentage used is at 13% so you still have more than ten years of specified life at your current write rate.

What model is this? It probably has a TBW (terabytes written) spec of 100 or so.