On Wed, Nov 23 2016 at 1:28pm -0500,
Bart Van Assche wrote:
> On 11/22/2016 07:16 PM, Mike Snitzer wrote:
> >Anyway, this _untested_ patch should hopefully resolve the 'all_blk_mq'
> >inconsistency you saw:
> >
> >diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
> >index 8b013ea..8ce81
On 11/22/2016 07:16 PM, Mike Snitzer wrote:
Anyway, this _untested_ patch should hopefully resolve the 'all_blk_mq'
inconsistency you saw:
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 8b013ea..8ce81d0 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -924,12 +
On Tue, Nov 22 2016 at 7:48P -0500,
Mike Snitzer wrote:
> But regardless, what certainly needs fixing is the inconsistency of
> inheriting DM_TYPE_MQ_REQUEST_BASED but not setting all_blk_mq to true
> (all_blk_mq == true is implied by DM_TYPE_MQ_REQUEST_BASED).
>
> I'm now questioning why we e
On Tue, Nov 22 2016 at 6:47pm -0500,
Bart Van Assche wrote:
> On 11/21/2016 04:34 PM, Mike Snitzer wrote:
> >But you WARN_ON_ONCE(clone && q->mq_ops) will trigger with sq-on-mq.
>
> Hello Mike,
>
> This behavior is indeed triggered by the sq-on-mq test. After having
> added the following code
On 11/21/2016 04:34 PM, Mike Snitzer wrote:
But you WARN_ON_ONCE(clone && q->mq_ops) will trigger with sq-on-mq.
Hello Mike,
This behavior is indeed triggered by the sq-on-mq test. After having
added the following code in __bind():
if (old_map &&
dm_table_all_blk_mq_devi
On Mon, Nov 21 2016 at 6:57pm -0500,
Bart Van Assche wrote:
> On 11/21/2016 03:43 PM, Mike Snitzer wrote:
> >Shouldn't be possible. The previous stacktrace you shared clearly
> >showed that the DM mpath request_queue was using blk-mq (dm_mq_queue_rq
> >was in the stack).
> >
> >Whereas the stac
On 11/21/2016 03:43 PM, Mike Snitzer wrote:
Shouldn't be possible. The previous stacktrace you shared clearly
showed that the DM mpath request_queue was using blk-mq (dm_mq_queue_rq
was in the stack).
Whereas the stacktrace above is clearly the old request_fn interface.
I'm unaware of how the
On Mon, Nov 21 2016 at 4:44pm -0500,
Bart Van Assche wrote:
> On 11/15/2016 04:37 PM, Mike Snitzer wrote:
> > On Tue, Nov 15 2016 at 6:35pm -0500,
> > Bart Van Assche wrote:
> >
> >> If a single-queue dm device is stacked on top of multi-queue block
> >> devices and map_tio_request() is calle
On 11/15/2016 04:37 PM, Mike Snitzer wrote:
> On Tue, Nov 15 2016 at 6:35pm -0500,
> Bart Van Assche wrote:
>
>> If a single-queue dm device is stacked on top of multi-queue block
>> devices and map_tio_request() is called while there are no paths then
>> the request will be prepared for a singl
On Tue, Nov 15 2016 at 8:08pm -0500,
Bart Van Assche wrote:
> On 11/15/2016 05:01 PM, Mike Snitzer wrote:
> >On Tue, Nov 15 2016 at 7:40pm -0500,
> >Bart Van Assche wrote:
> >>Are you aware that dm_table_determine_type() sets "all_blk_mq" to
> >>false if there are no paths, even if the dm devi
On 11/15/2016 05:01 PM, Mike Snitzer wrote:
On Tue, Nov 15 2016 at 7:40pm -0500,
Bart Van Assche wrote:
Are you aware that dm_table_determine_type() sets "all_blk_mq" to
false if there are no paths, even if the dm device is in blk-mq
mode?
That shouldn't matter. Once the type is established
On Tue, Nov 15 2016 at 7:40pm -0500,
Bart Van Assche wrote:
> On 11/15/2016 04:37 PM, Mike Snitzer wrote:
> >On Tue, Nov 15 2016 at 6:35pm -0500,
> >Bart Van Assche wrote:
> >>If a single-queue dm device is stacked on top of multi-queue block
> >>devices and map_tio_request() is called while t
On 11/15/2016 04:37 PM, Mike Snitzer wrote:
On Tue, Nov 15 2016 at 6:35pm -0500,
Bart Van Assche wrote:
If a single-queue dm device is stacked on top of multi-queue block
devices and map_tio_request() is called while there are no paths then
the request will be prepared for a single-queue path.
On Tue, Nov 15 2016 at 6:35pm -0500,
Bart Van Assche wrote:
> If a single-queue dm device is stacked on top of multi-queue block
> devices and map_tio_request() is called while there are no paths then
> the request will be prepared for a single-queue path. If a path is
> added after a request wa
If a single-queue dm device is stacked on top of multi-queue block
devices and map_tio_request() is called while there are no paths then
the request will be prepared for a single-queue path. If a path is
added after a request was prepared and before __multipath_map() is
called return DM_MAPIO_REQUE
15 matches
Mail list logo
