From: kbusch@kernel.org (Keith Busch)
Subject: [PATCH rfc 1/2] nvme: don't remove namespace if revalidate failed because of controller reset
Date: Thu, 1 Aug 2019 08:33:31 -0600 [thread overview]
Message-ID: <20190801143331.GC15795@localhost.localdomain> (raw)
In-Reply-To: <55631812-bc90-9dc1-53b7-a76696a7140e@grimberg.me>
On Wed, Jul 31, 2019@06:13:06PM -0700, Sagi Grimberg wrote:
>
> >> Well, I don't think we should do that. Unlike I/O commands, which can
> >> failover to a different path, these admin commands are bound to the
> >> specific controller. In case it takes minutes/hours/days for the
> >> controller to restore normal operation, it will be unpleasant to say
> >> the least to have admin operations get stuck for so long.
> >
> > Unpleasant for who? The scan_work is the only thing waiting for these
> > commands, no one else should care because you can't run IO if you're
> > stuck in very long reset anyway.
>
> The hung task detector would care, and a user who will attempt to issue
> a passthru command, and the rest of the system that have one of the
> kworkers sacrificed for a significant amount of time...
blk_execute_rq already defeats hung task detection for stalled IO.
My point, though, was passthru doesn't care about scan_work. A submitted
passthru command is blocked for reset, so blocking scan_work doesn't
make that situation any better or worse.
> > I think the main point is that we don't want to take a delete action on
> > a transient condition, but sprinkling NVME_CTRL_LIVE checks is open to
> > many other races.
>
> Hence I suggested the transport error code...
That should work too.
next prev parent reply other threads:[~2019-08-01 14:33 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-29 23:31 [PATCH rfc 0/2] nvme controller reset and namespace scan work race conditions Sagi Grimberg
2019-07-29 23:32 ` [PATCH rfc 1/2] nvme: don't remove namespace if revalidate failed because of controller reset Sagi Grimberg
2019-07-30 0:59 ` Keith Busch
2019-07-30 1:04 ` Sagi Grimberg
2019-07-30 1:04 ` Ming Lei
2019-07-30 1:06 ` Sagi Grimberg
2019-07-30 1:10 ` Ming Lei
2019-07-30 1:19 ` Sagi Grimberg
2019-07-30 1:30 ` Ming Lei
2019-07-30 1:40 ` Sagi Grimberg
2019-07-30 2:09 ` Ming Lei
2019-07-30 17:12 ` Sagi Grimberg
2019-07-30 17:30 ` Keith Busch
2019-07-30 18:15 ` Sagi Grimberg
2019-07-31 7:13 ` Hannes Reinecke
2019-07-31 18:08 ` Sagi Grimberg
2019-07-31 7:01 ` Hannes Reinecke
2019-07-31 14:16 ` Keith Busch
2019-07-31 18:03 ` Sagi Grimberg
2019-07-31 19:32 ` Keith Busch
2019-07-31 20:08 ` Sagi Grimberg
2019-07-31 20:16 ` Keith Busch
2019-07-31 20:45 ` Sagi Grimberg
2019-07-31 20:58 ` Keith Busch
2019-07-31 21:14 ` Sagi Grimberg
2019-07-31 21:54 ` Keith Busch
2019-08-01 1:13 ` Sagi Grimberg
2019-08-01 14:33 ` Keith Busch [this message]
2019-08-01 18:52 ` Sagi Grimberg
2019-07-31 6:58 ` Hannes Reinecke
2019-07-31 18:11 ` Sagi Grimberg
2019-07-31 20:02 ` Hannes Reinecke
2019-07-31 20:16 ` Sagi Grimberg
2019-07-31 12:18 ` Hannes Reinecke
2019-07-31 18:16 ` Sagi Grimberg
2019-07-31 20:04 ` Hannes Reinecke
2019-07-31 20:37 ` Sagi Grimberg
2019-07-29 23:32 ` [PATCH rfc 2/2] nvme: fix possible use-after-free condition when controller reset is racing namespace scanning Sagi Grimberg
2019-07-31 12:23 ` Hannes Reinecke
2019-07-31 18:21 ` Sagi Grimberg
2019-08-01 7:24 ` Hannes Reinecke
2019-08-01 18:46 ` Sagi Grimberg
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=20190801143331.GC15795@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