linux-nvme.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Hannes Reinecke <hare@suse.de>
To: "Knight, Frederick" <Frederick.Knight@netapp.com>,
	Daniel Wagner <dwagner@suse.de>,
	John Meneghini <jmeneghi@redhat.com>
Cc: Sagi Grimberg <sagi@grimberg.me>,
	"linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>,
	Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Subject: Re: [PATCH v2] nvmet: force reconnect when number of queue changes
Date: Fri, 30 Sep 2022 08:32:49 +0200	[thread overview]
Message-ID: <5506f1d3-3f46-9be4-ae22-66bbc4f053bd@suse.de> (raw)
In-Reply-To: <DM8PR06MB7704CA28602F1367574EB23CF1549@DM8PR06MB7704.namprd06.prod.outlook.com>

On 9/28/22 20:02, Knight, Frederick wrote:
> Reset and Disconnect are different.
> 
> Reset uses registers (and therefore Get Property and Set Property commands) over a valid connection.
> 
> Disconnect causes a reset (you have to reconnect to the reset controller)
> Reset does not cause an immediate disconnect.
> 
This probably is a confusion with how the linux implementation works.
For linux NVMe-oF a reset is equivalent to a reconnect (ie disconnect 
followed by a reconnect), as for linux _any_ error will be escalated to 
be equivalent to a connection error.
Hence a pure 'reset' using Get/Set Property is never attempted.

Cheers,

Hannes

>> -----Original Message-----
>> From: Daniel Wagner <dwagner@suse.de>
>> Sent: Wednesday, September 28, 2022 11:26 AM
>> To: John Meneghini <jmeneghi@redhat.com>
>> Cc: Knight, Frederick <Frederick.Knight@netapp.com>; Sagi Grimberg
>> <sagi@grimberg.me>; linux-nvme@lists.infradead.org; Shinichiro Kawasaki
>> <shinichiro.kawasaki@wdc.com>; hare@suse.de
>> Subject: Re: [PATCH v2] nvmet: force reconnect when number of queue
>> changes
>>
>> NetApp Security WARNING: This is an external email. Do not click links or
>> open attachments unless you recognize the sender and know the content is
>> safe.
>>
>>
>>
>>
>> On Wed, Sep 28, 2022 at 11:01:00AM -0400, John Meneghini wrote:
>>> So this is one place where I think we conflate NVMe-oF with NVMe in
>>> the specification.  If "reset" == "disconnect", then Daniel's patches
>>> just implemented support for something which is forbidden by the spec
>>> - a controller that changes the number of IOQs between resets.
>>
>> FWIW, the scenario I described is from a real world experience. So even if it
>> is forbidden by the spec, it exists.

-- 
Dr. Hannes Reinecke                Kernel Storage Architect
hare@suse.de                              +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman



      parent reply	other threads:[~2022-09-30  6:33 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-27 14:31 [PATCH v2] nvmet: force reconnect when number of queue changes Daniel Wagner
2022-09-27 15:01 ` Daniel Wagner
2022-09-28  6:55 ` Sagi Grimberg
2022-09-28  7:48   ` Daniel Wagner
2022-09-28  8:31     ` Sagi Grimberg
2022-09-28  9:02       ` Daniel Wagner
2022-09-28 12:39         ` Knight, Frederick
2022-09-28 13:50           ` Daniel Wagner
2022-09-28 14:23             ` Sagi Grimberg
2022-09-28 15:21               ` Hannes Reinecke
2022-09-28 16:01               ` Knight, Frederick
2022-10-05 18:15               ` Daniel Wagner
2022-10-06 11:37                 ` Sagi Grimberg
2022-10-06 20:15                   ` James Smart
2022-10-06 20:54                     ` Knight, Frederick
2022-09-28 16:01             ` Knight, Frederick
2022-09-28 15:01           ` John Meneghini
2022-09-28 15:26             ` Daniel Wagner
2022-09-28 18:02               ` Knight, Frederick
2022-09-29  2:14                 ` John Meneghini
2022-09-29  3:04                   ` Knight, Frederick
2022-09-30  7:03                   ` Hannes Reinecke
2022-09-30  6:32                 ` Hannes Reinecke [this message]

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=5506f1d3-3f46-9be4-ae22-66bbc4f053bd@suse.de \
    --to=hare@suse.de \
    --cc=Frederick.Knight@netapp.com \
    --cc=dwagner@suse.de \
    --cc=jmeneghi@redhat.com \
    --cc=linux-nvme@lists.infradead.org \
    --cc=sagi@grimberg.me \
    --cc=shinichiro.kawasaki@wdc.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).