On Tue, 2017-08-08 at 09:22 -0700, Greg KH wrote:

On Sun, Jul 30, 2017 at 03:50:15PM +0200, Oleksandr Natalenko wrote:

quoted

Hello Mike et al.
=20
On ned=C4=9Ble 30. =C4=8Dervence 2017 7:12:31 CEST Mike Galbraith wrote=

:

quoted

quoted

FWIW, first thing I'd do is update that 4.12.0 to 4.12.4, and see if
stable fixed it.

=20
My build already includes v4.12.4.
=20

quoted

If not, I'd find these two commits irresistible.
=20
5f042e7cbd9eb blk-mq: Include all present CPUs in the default queue m=

apping

quoted

quoted

4b855ad37194f blk-mq: Create hctx for each present CPU

=20
I've applied these 2 commits, and cannot reproduce the issue anymore. L=

ooks=20

quoted

like a perfect hit, thanks!
=20

quoted

'course applying random upstream bits does come with some risk, tryin=

g

quoted

quoted

a kernel already containing them has less "entertainment" potential.=

=20

quoted

=20
Should you consider applying them to v4.12.x stable series? CC'ing Greg=

 just=20

quoted

in case.

=20
I can queue these up if I get an ack from the developers/maintainers
that it is ok to do so...
=20
{hint}

{hint++}

Those commits take Steven Rostedt's hotplug stress script runtime down
from 4 _minutes_ down to 7 seconds for my RT tree, so I'm rather hoping
you hear an "ACK" too.

	-Mike