All of lore.kernel.org
 help / color / mirror / Atom feed
From: Martin Wilck <mwilck@suse.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Mike Snitzer <snitzer@redhat.com>,
	linux-scsi@vger.kernel.org, Daniel Wagner <dwagner@suse.de>,
	emilne@redhat.com, linux-block@vger.kernel.org,
	dm-devel@redhat.com, Paolo Bonzini <pbonzini@redhat.com>,
	"Martin K. Petersen" <martin.petersen@oracle.com>,
	nkoenig@redhat.com, Bart Van Assche <Bart.VanAssche@sandisk.com>,
	Alasdair G Kergon <agk@redhat.com>
Subject: Re: [dm-devel] [PATCH v5 3/3] dm mpath: add CONFIG_DM_MULTIPATH_SG_IO - failover for SG_IO
Date: Fri, 02 Jul 2021 16:21:01 +0200	[thread overview]
Message-ID: <003727e7a195cb0f525cc2d7abda3a19ff16eb98.camel@suse.com> (raw)
In-Reply-To: <20210701113442.GA10793@lst.de>

On Do, 2021-07-01 at 13:34 +0200, Christoph Hellwig wrote:
> On Thu, Jul 01, 2021 at 12:35:53PM +0200, Martin Wilck wrote:
> > I respectfully disagree. Users of dm-multipath devices expect that
> > IO
> > succeeds as long as there's at least one healthy path. This is a
> > fundamental property of multipath devices. Whether IO is sent
> > "normally" or via SG_IO doesn't make a difference wrt this
> > expectation.
> 
> If you have those (pretty reasonable) expections don't use SG_IO.
> That is what the regular read/write path is for.  SG_IO gives you
> raw access to the SCSI logic unit, and you get to keep the pieces
> if anything goes wrong.

With this logic, if some paths are down, SG_IO commands on multipath
devices yield random results. On one path a command would fail, and on
another it would succeed. User space has no way to control or even see
what path is being used. That's a very fragile user space API, on the
fringe of being useless IMO.

If user space is interested in the error handling semantics you
describe, it can run SG_IO on individual SCSI devices any time. With
the change I am proposing, nothing is lost for user space. If user
space decides to do SG_IO on a multipath device, it has a different
expectation, which my patch set implements. IMO we should strive to
match the semantics for ioctls on natively multipathed NVMe namespaces.

Regards
Martin



WARNING: multiple messages have this Message-ID (diff)
From: Martin Wilck <mwilck@suse.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Assche <Bart.VanAssche@sandisk.com>,
	linux-scsi@vger.kernel.org, Wagner <dwagner@suse.de>,
	Mike Snitzer <snitzer@redhat.com>,
	emilne@redhat.com, linux-block@vger.kernel.org,
	dm-devel@redhat.com, Daniel,
	"Martin K. Petersen" <martin.petersen@oracle.com>,
	nkoenig@redhat.com, Paolo Bonzini <pbonzini@redhat.com>,
	Alasdair G Kergon <agk@redhat.com>,
	Bart
Subject: Re: [dm-devel] [PATCH v5 3/3] dm mpath: add CONFIG_DM_MULTIPATH_SG_IO - failover for SG_IO
Date: Fri, 02 Jul 2021 16:21:01 +0200	[thread overview]
Message-ID: <003727e7a195cb0f525cc2d7abda3a19ff16eb98.camel@suse.com> (raw)
In-Reply-To: <20210701113442.GA10793@lst.de>

On Do, 2021-07-01 at 13:34 +0200, Christoph Hellwig wrote:
> On Thu, Jul 01, 2021 at 12:35:53PM +0200, Martin Wilck wrote:
> > I respectfully disagree. Users of dm-multipath devices expect that
> > IO
> > succeeds as long as there's at least one healthy path. This is a
> > fundamental property of multipath devices. Whether IO is sent
> > "normally" or via SG_IO doesn't make a difference wrt this
> > expectation.
> 
> If you have those (pretty reasonable) expections don't use SG_IO.
> That is what the regular read/write path is for.  SG_IO gives you
> raw access to the SCSI logic unit, and you get to keep the pieces
> if anything goes wrong.

With this logic, if some paths are down, SG_IO commands on multipath
devices yield random results. On one path a command would fail, and on
another it would succeed. User space has no way to control or even see
what path is being used. That's a very fragile user space API, on the
fringe of being useless IMO.

If user space is interested in the error handling semantics you
describe, it can run SG_IO on individual SCSI devices any time. With
the change I am proposing, nothing is lost for user space. If user
space decides to do SG_IO on a multipath device, it has a different
expectation, which my patch set implements. IMO we should strive to
match the semantics for ioctls on natively multipathed NVMe namespaces.

Regards
Martin



--
dm-devel mailing list
dm-devel@redhat.com
https://listman.redhat.com/mailman/listinfo/dm-devel


  reply	other threads:[~2021-07-02 14:21 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-28 15:15 [PATCH v5 0/3] scsi/dm: dm_blk_ioctl(): implement failover for SG_IO on dm-multipath mwilck
2021-06-28 15:15 ` [dm-devel] " mwilck
2021-06-28 15:15 ` [PATCH v5 1/3] scsi: scsi_ioctl: export __scsi_result_to_blk_status() mwilck
2021-06-28 15:15   ` [dm-devel] " mwilck
2021-06-28 15:15 ` [PATCH v5 2/3] scsi: scsi_ioctl: add sg_io_to_blk_status() mwilck
2021-06-28 15:15   ` [dm-devel] " mwilck
2021-06-28 15:15 ` [PATCH v5 3/3] dm mpath: add CONFIG_DM_MULTIPATH_SG_IO - failover for SG_IO mwilck
2021-06-28 15:15   ` [dm-devel] " mwilck
2021-07-01  7:56   ` Christoph Hellwig
2021-07-01  7:56     ` [dm-devel] " Christoph Hellwig
2021-07-01 10:35     ` Martin Wilck
2021-07-01 10:35       ` [dm-devel] " Martin Wilck
2021-07-01 11:34       ` Christoph Hellwig
2021-07-01 11:34         ` [dm-devel] " Christoph Hellwig
2021-07-02 14:21         ` Martin Wilck [this message]
2021-07-02 14:21           ` Martin Wilck
2021-07-05 13:02           ` Paolo Bonzini
2021-07-05 13:02             ` Paolo Bonzini
2021-07-05 13:11             ` Hannes Reinecke
2021-07-05 13:11               ` Hannes Reinecke
2021-07-05 13:48               ` Martin Wilck
2021-07-05 13:48                 ` Martin Wilck
2021-07-06 10:13                 ` Paolo Bonzini
2021-07-06 10:13                   ` Paolo Bonzini
2021-07-01 11:06     ` Paolo Bonzini
2021-07-01 11:06       ` [dm-devel] " Paolo Bonzini

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=003727e7a195cb0f525cc2d7abda3a19ff16eb98.camel@suse.com \
    --to=mwilck@suse.com \
    --cc=Bart.VanAssche@sandisk.com \
    --cc=agk@redhat.com \
    --cc=dm-devel@redhat.com \
    --cc=dwagner@suse.de \
    --cc=emilne@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=nkoenig@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=snitzer@redhat.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.