[dm-devel] dm-mq and end_clone_request()
Mike Snitzer
snitzer at redhat.com
Thu Jul 21 20:32:09 UTC 2016
On Wed, Jul 20 2016 at 1:37pm -0400,
Bart Van Assche <bart.vanassche at sandisk.com> wrote:
> On 07/20/2016 07:27 AM, Mike Snitzer wrote:
> >On Wed, Jul 20 2016 at 10:08am -0400,
> >Mike Snitzer <snitzer at redhat.com> wrote:
> >[ ... ]
> >diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
> >index 7a96618..347ff25 100644
> >--- a/drivers/md/dm-rq.c
> >+++ b/drivers/md/dm-rq.c
> >@@ -414,7 +414,7 @@ static void dm_complete_request(struct request *rq, int error)
> > if (!rq->q->mq_ops)
> > blk_complete_request(rq);
> > else
> >- blk_mq_complete_request(rq, error);
> >+ blk_mq_complete_request(rq, 0);
> > }
> >
> > /*
>
> Hello Mike,
>
> Thanks for the patch. But unfortunately even with this patch applied
> I see fio reporting I/O errors when run on top of dm-mq after a
> (simulated) cable pull.
BTW, curious, how is it that you're simulating the cable pull? I'd like
to see if doing the same, via a new test in mptest, exposes this issue
you're hitting.
Mike
More information about the dm-devel
mailing list