NVME aborting outstanding i/o

Chuck Tuffli chuck at freebsd.org
Thu Apr 4 15:22:29 UTC 2019


On Thu, Apr 4, 2019 at 4:27 AM Patrick M. Hausen <hausen at punkt.de> wrote:
>
> Hi,
>
> > Am 04.04.2019 um 10:37 schrieb Patrick M. Hausen <hausen at punkt.de>:
> > But:
> >
> >       root at freenas01[~]# sysctl hw.nvme.per_cpu_io_queues
> >       sysctl: unknown oid 'hw.nvme.per_cpu_io_queues'
> >       root at freenas01[~]# sysctl hw.nvme.min_cpus_per_ioq
> >       sysctl: unknown oid 'hw.nvme.min_cpus_per_ioq'
> >       root at freenas01[~]# sysctl hw.nvme.force_intx
> >       sysctl: unknown oid 'hw.nvme.force_intx'
>
> Looks like these can be set via loader.conf and reboot although
> they are not visible in the running system. Even when set they
> are not visible afterwards ...
>
>         hw.nvme.per_cpu_io_queues=0
>
> seems to cure the NVME errors. I’m still curious about the root
> problem here, bit at least I can now continue to use the machines
> for some real loads.

Out of curiosity, what device is this? I.e. nvmecontrol identify nvme7

--chuck


More information about the freebsd-stable mailing list