On Thu, May 18, 2017 at 12:06:24PM -0400, Keith Busch wrote:
> On Thu, May 18, 2017 at 11:35:43PM +0800, Ming Lei wrote:
> > On Thu, May 18, 2017 at 03:49:31PM +0200, Christoph Hellwig wrote:
> > > On Wed, May 17, 2017 at 09:27:29AM +0800, Ming Lei wrote:
> > > > If some writeback requests are subm
On Thu, May 18, 2017 at 11:35:43PM +0800, Ming Lei wrote:
> On Thu, May 18, 2017 at 03:49:31PM +0200, Christoph Hellwig wrote:
> > On Wed, May 17, 2017 at 09:27:29AM +0800, Ming Lei wrote:
> > > If some writeback requests are submitted just before queue is killed,
> > > and these requests may not b
On Thu, May 18, 2017 at 03:49:31PM +0200, Christoph Hellwig wrote:
> On Wed, May 17, 2017 at 09:27:29AM +0800, Ming Lei wrote:
> > If some writeback requests are submitted just before queue is killed,
> > and these requests may not be canceled in nvme_dev_disable() because
> > they are not started
On Wed, May 17, 2017 at 09:27:29AM +0800, Ming Lei wrote:
> If some writeback requests are submitted just before queue is killed,
> and these requests may not be canceled in nvme_dev_disable() because
> they are not started yet, it is still possible for blk-mq to hold
> these requests in .requeue l
If some writeback requests are submitted just before queue is killed,
and these requests may not be canceled in nvme_dev_disable() because
they are not started yet, it is still possible for blk-mq to hold
these requests in .requeue list.
So we have to abort these requests first before del_gendisk(