From: kbusch@kernel.org (Keith Busch)
Subject: [PATCH 3/6] nvme-pci: Unblock reset_work on IO failure
Date: Thu, 16 May 2019 08:14:36 -0600 [thread overview]
Message-ID: <20190516141435.GB23333@localhost.localdomain> (raw)
In-Reply-To: <20190516031333.GC16342@ming.t460p>
On Wed, May 15, 2019@08:13:35PM -0700, Ming Lei wrote:
> On Wed, May 15, 2019@10:36:22AM -0600, Keith Busch wrote:
> > + nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
> > + /* fall through */
> > + case NVME_CTRL_DELETING:
> > dev_warn_ratelimited(dev->ctrl.device,
> > "I/O %d QID %d timeout, disable controller\n",
> > req->tag, nvmeq->qid);
> > - nvme_dev_disable(dev, shutdown);
> > + nvme_dev_disable(dev, true);
> > nvme_req(req)->flags |= NVME_REQ_CANCELLED;
> > return BLK_EH_DONE;
> > case NVME_CTRL_RESETTING:
>
> Then the controller is dead, and can't work any more together with data
> loss. I guess this way is too violent from user view.
Indeed, it is a bit harsh; however, it is definitely better than having a
stuck controller unable to make forward progress. We may be able to do
better, but I think this patch is a step in the right direction.
next prev parent reply other threads:[~2019-05-16 14:14 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-15 16:36 [PATCH 1/6] nvme-pci: Fix controller freeze wait disabling Keith Busch
2019-05-15 16:36 ` [PATCH 2/6] nvme-pci: Don't disable on timeout in reset state Keith Busch
2019-05-16 3:07 ` Ming Lei
2019-05-16 14:33 ` Keith Busch
2019-05-16 6:27 ` Christoph Hellwig
2019-05-15 16:36 ` [PATCH 3/6] nvme-pci: Unblock reset_work on IO failure Keith Busch
2019-05-16 3:13 ` Ming Lei
2019-05-16 14:14 ` Keith Busch [this message]
2019-05-17 2:31 ` Ming Lei
2019-05-16 6:28 ` Christoph Hellwig
2019-05-15 16:36 ` [PATCH 4/6] nvme-pci: Sync queues on reset Keith Busch
2019-05-16 3:34 ` Ming Lei
2019-05-16 6:29 ` Christoph Hellwig
2019-05-16 14:08 ` Keith Busch
2019-05-16 13:43 ` Minwoo Im
2019-05-15 16:36 ` [PATCH 5/6] nvme: Export get and set features Keith Busch
2019-05-16 6:26 ` Christoph Hellwig
2019-05-16 13:47 ` Minwoo Im
2019-05-15 16:36 ` [PATCHv2 6/6] nvme-pci: Use host managed power state for suspend Keith Busch
2019-05-15 19:33 ` Mario.Limonciello
2019-05-15 19:34 ` Keith Busch
2019-05-15 19:43 ` Mario.Limonciello
2019-05-16 6:25 ` Christoph Hellwig
2019-05-16 14:24 ` Keith Busch
2019-05-17 9:08 ` Christoph Hellwig
2019-05-16 9:29 ` Rafael J. Wysocki
2019-05-16 14:26 ` Keith Busch
2019-05-16 18:27 ` Kai-Heng Feng
2019-05-16 18:33 ` Mario.Limonciello
2019-05-16 19:38 ` Keith Busch
2019-05-16 20:25 ` Rafael J. Wysocki
2019-05-16 20:39 ` Keith Busch
2019-05-16 20:56 ` Rafael J. Wysocki
2019-05-17 8:39 ` Rafael J. Wysocki
2019-05-17 9:05 ` Christoph Hellwig
2019-05-17 9:17 ` Rafael J. Wysocki
2019-05-17 9:35 ` Christoph Hellwig
2019-05-17 10:34 ` Rafael J. Wysocki
2019-05-22 6:47 ` Kai Heng Feng
2019-05-22 15:52 ` Christoph Hellwig
2019-05-22 16:02 ` Keith Busch
2019-05-22 16:35 ` Mario.Limonciello
2019-05-22 16:56 ` Keith Busch
2019-05-22 23:08 ` Keith Busch
2019-05-23 15:27 ` Keith Busch
2019-05-17 9:22 ` Kai-Heng Feng
2019-05-17 9:32 ` Rafael J. Wysocki
2019-05-16 20:24 ` Rafael J. Wysocki
2019-05-16 2:43 ` [PATCH 1/6] nvme-pci: Fix controller freeze wait disabling Ming Lei
2019-05-17 18:40 ` Keith Busch
2019-05-16 6:27 ` Christoph Hellwig
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190516141435.GB23333@localhost.localdomain \
--to=kbusch@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox