On 3/3/21 3:25 PM, Stuart Henderson wrote:
On 2021/03/03 15:10, Karel Gardas wrote:
Looks like you are not the only one having issue with AMD chipset and new
samsung SSD:
https://eu.community.samsung.com/t5/computers-it/860-evo-250gb-causing-freezes-on-amd-system/td-p/575813/page/2
https://community.amd.com/t5/drivers-software/990fx-sb950-chipset-drivers-not-working-with-samsung-860-pro-ssd/td-p/100175
And here you even have a trace of issues in Linux kernel bugzilla:
https://bugzilla.kernel.org/show_bug.cgi?id=201693
If you read all info on those pages, you will find some workarounds for you
to test, but generally speaking I'm afraid this hardware combination
does not seem to be too trustful...
"So I guess we should consider doing a kernel side quirk where the
kernel disables NCQ on the combination of having a Samsung 860 or 870
SSD with a SATA controller on these older AMD chipsets. This does
require having a list of PCI-ids for the controllers on which to enable
this quirk."
ouch
Indeed, but I would rather advice using workaround mentioned -- go to
BIOS and switch from AHCI to IDE when situation requires that.
Obvious non-optimality of this solution is that this switches NCQ off
also on perfectly fine port/drive combinations but on the other hand
the question is if some of core developers will be interested enough in
working around this issue
and patching sys for just this not so common combination of hardware,
but on the other hand,
Mark, since you do have hardware to test, are you able to develop and
push the patch to tech@ ?
