nvme0: async event occurred (log page id=0x2)

Warner Losh imp at bsdimp.com
Fri May 4 04:07:12 UTC 2018


On Thu, May 3, 2018 at 9:56 PM, Craig Leres <leres at freebsd.org> wrote:

> I have an intel nuc (NUC6i3SYH) that ran 10.3-RELEASE until a few weeks
> ago and now 11.1-RELEASE. The system disk is an intel 600p M.2 SSD and
> there is also a 2TB seagate laptop drive (ST2000LM007).
>
> Occasionally the system SSD will go to sleep. It happened today with
> this on the console:
>
>     nvme0: async event occurred (log page id=0x2)
>     nvme0: resetting controller
>     nvme0: nvme_ctrlr_wait_for_ready called with desired_val = 0 but
> cc.en = 1
>
> Later it would occasionally print out:
>
>      swap_pager: indefinite wait buffer: bufobj: 0, blkno: 1509, size:
> 12200
>
> There was an app playing music from the 2TB drive that was still working
> when I reset the box. But no i/o was occurring with with the M.2 SSD.
>
> I see PR 209571 might be related (same async event log anyway at least).
>


> Does anyone have suggestions for me?
>

Async events are 'something went wrong' messages. Log page 2 is the smart
log page.

what does 'nvmecontrol logpage -p 2 nvme0' tell you right after this
happens.  My guess is that it's overheating.

Warner


More information about the freebsd-hackers mailing list