NVME aborting outstanding i/o

[Patrick M. Hausen]

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.

Kind regards,
Patrick
-- 
punkt.de GmbH			Internet - Dienstleistungen - Beratung
Kaiserallee 13a			Tel.: 0721 9109-0 Fax: -100
76133 Karlsruhe			info at punkt.de	http://punkt.de
AG Mannheim 108285		Gf: Juergen Egeling