Soliciting opinions on dsched removal

Markus Pfeiffer markus.pfeiffer at morphism.de
Sun Nov 8 16:09:36 PST 2015


Hi,

On Sun, Nov 08, 2015 at 05:03:33PM -0500, Alex Hornung wrote:
> On 08/11/2015 10:38, Matthew Dillon wrote:
> >     The basic problem is that heavy use of dsched (the disk scheduler) has
> >     caused crashes and lockups ever since dsched went into the tree, and is
> >     still causing crashes and lockups today.  Several people have tried to 
> >     bandaid it but honestly I think the only correct solution is to remove it
> >     and then start over from scratch at some future date with a better design.
> >
> >     So I would like to remove it, and I am soliciting opinions on that.
> I'm all for it.

I am completely with Alex on this one, in particular the comments about SSD,
and probably even more so NVMe warrant changing the approach to IO scheduling.
In particular simplifying the CAM interface seems worth a shot.

Not that I want to stop anyone from trying...

Cheers,
Markus
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: not available
URL: <http://lists.dragonflybsd.org/pipermail/kernel/attachments/20151109/86e19763/attachment-0011.bin>


More information about the Kernel mailing list