NVME aborting outstanding i/o and controller resets
Patrick M. Hausen
hausen at punkt.de
Sun Apr 14 13:01:48 UTC 2019
> Am 13.04.2019 um 02:37 schrieb Warner Losh <imp at bsdimp.com>:
> > There's been some minor improvements in -current here. Any chance you could experimentally try that with this test? You won't get as many I/O abort errors (since we don't print those), and we have a few more workarounds for the reset path (though honestly, it's still kinda stinky).
> HEAD or RELENG_12, too?
> HEAD is preferred, but any recent snapshot will do.
I could not reproduce the problem for a couple of hours with
an otherwise identical system but only 4 of these Intel drives.
Now the same test system with 6 drives just as our FreeNAS boxes
- instantly reproducible.
I’ll upgrade to HEAD and see if that changes anything.
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
More information about the freebsd-stable