nvme controller is down; will reset

[alekzunder]

Yes, requested me full hardware configuration. Offered add kernel options: libata.allow_tpm=1 nvme_core.default_ps_max_latency_us=0
In general, nothing interesting. There were a weekend, maybe they will write something today. Waiting....

[digitaloxide42]

Kingston solid states are actually pretty good, we have had better luck with them than samsung lately, and we go through a lot of hard drives at my office.


That being said I think you won the silicon lottery on this one, it certianly looks like you have a bad SSD drive. But I would also upgrade your motherboard, processor and ram while your at it... I've never liked the pcie expansion cards for nvme slots very much, its much better to have a board with native nvme slots in my opinion.

[alekzunder]

I got answer from support of Kingston: return to the store.

Addition:
I repeated check over fio, and noticed, that nvme controller down, if temperature more then 47...48 degrees!
I bought a new NVME Samsung, check fio. It work fine! At temperature above 60 degrees!
I'm shure that case in heated of NVME-controller.

I don't close topic yet...

Addition: on new nvme SSD, the error counter is also growing. How critical is it? I found https://github.com/linux-nvme/nvme-c...ent-1862744947

sudo nvme error-log /dev/nvme0n1
Error Log Entries for device:nvme0n1 entries:64
.................
 Entry[ 0]   
.................
error_count    : 3
sqid        : 0
cmdid        : 0x4009
status_field    : 0x2002(INVALID_FIELD: A reserved coded value or an unsupported value in a defined field)
phase_tag    : 0
parm_err_loc    : 0xffff
lba        : 0
nsid        : 0
vs        : 0
trtype        : The transport type is not indicated or the error is not transport related.
cs        : 0
trtype_spec_info: 0
.................