public inbox for linux-scsi@vger.kernel.org
 help / color / mirror / Atom feed
From: Damien Le Moal <damien.lemoal@opensource.wdc.com>
To: Bart Van Assche <bvanassche@acm.org>,
	Niklas Cassel <niklas.cassel@wdc.com>,
	Paolo Valente <paolo.valente@linaro.org>,
	Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>, Hannes Reinecke <hare@suse.de>,
	linux-scsi@vger.kernel.org, linux-ide@vger.kernel.org,
	linux-block@vger.kernel.org
Subject: Re: [PATCH v3 01/18] block: introduce duration-limits priority class
Date: Wed, 25 Jan 2023 06:48:21 +0900	[thread overview]
Message-ID: <6329e4fb-536b-00da-b38c-b6cb95f68994@opensource.wdc.com> (raw)
In-Reply-To: <bd75a7d8-7664-eff5-d417-a2fa8708fb05@acm.org>

On 1/25/23 05:36, Bart Van Assche wrote:
> On 1/24/23 11:27, Bart Van Assche wrote:
>> Implementing duration limit support using the I/O priority mechanism 
>> makes it impossible to configure the I/O priority for commands that have 
>> a duration limit. Shouldn't the duration limit be independent of the I/O 
>> priority? Am I perhaps missing something?
> 
> (replying to my own e-mail)
> 
> In SAM-6 I found the following: "The device server may use the duration 
> expiration time to determine the order of processing commands with
> the SIMPLE task attribute within the task set. A difference in duration 
> expiration time between commands may override other scheduling 
> considerations (e.g., different times to access different logical block 
> addresses or vendor specific scheduling considerations). Processing of a 
> collection of commands with different command duration limit settings 
> should cause a command with an earlier duration expiration time to 
> complete with status sooner than a command with a later duration 
> expiration time."
> 
> Do I understand correctly that it is optional for a SCSI device to 
> interpret the command duration as a priority and that this is not mandatory?

This describes the expected behavior from the drive in terms of command
execution ordering when CDL is used. The text is a little "soft" and sound
as if this behavior is optional because CDL is a combination of time
limits AND a policy for each time limit. The policy of a CDL indicates
what the drive behavior should be if a command misses its time limit. In
short, there are 2 policies:
1) best-effort: the time limit is a hint of sorts. If the drive fails to
execute the command before the limit expires, the command is not aborted
and execution continues.
2) fast-fail: If the drive fails to execute the command before the time
limit expires, the command must be completed with an error immediately.

And CDL also has a field, settable by the user, that describes an allowed
performance degradation to achieve CDL scheduling in time. That is, most
important for the best-effort case to indicate how "serious" the user is
about the CDL limit "hint".

So as you can see I think, the SAM-6 text is vague because of the many
possible variations in scheduling policies that need to be implemented by
a drive.

-- 
Damien Le Moal
Western Digital Research


  reply	other threads:[~2023-01-24 21:48 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-24 19:02 [PATCH v3 00/18] Add Command Duration Limits support Niklas Cassel
2023-01-24 19:02 ` [PATCH v3 01/18] block: introduce duration-limits priority class Niklas Cassel
2023-01-24 19:27   ` Bart Van Assche
2023-01-24 20:36     ` Bart Van Assche
2023-01-24 21:48       ` Damien Le Moal [this message]
2023-01-24 21:29     ` Damien Le Moal
2023-01-24 22:43       ` Bart Van Assche
2023-01-24 22:59         ` Damien Le Moal
2023-01-25  0:05           ` Bart Van Assche
2023-01-25  1:19             ` Damien Le Moal
2023-01-25 18:37               ` Bart Van Assche
2023-01-25 21:23                 ` Niklas Cassel
2023-01-26  0:24                   ` Damien Le Moal
2023-01-26 13:53                     ` Niklas Cassel
2023-01-26 17:33                       ` Bart Van Assche
2023-01-27  0:18                         ` Damien Le Moal
2023-01-27  1:40                           ` Damien Le Moal
2023-01-27 17:23                             ` Bart Van Assche
2023-01-28  0:40                               ` Damien Le Moal
2023-01-28  0:47                                 ` Bart Van Assche
2023-01-28  0:59                                   ` Damien Le Moal
2023-01-28 20:25                                     ` Martin K. Petersen
2023-01-29  3:52                                       ` Damien Le Moal
2023-01-30 13:44                                         ` Hannes Reinecke
2023-01-30 14:55                                           ` Damien Le Moal
2023-01-30 19:24                                         ` Bart Van Assche
2023-01-30 20:40                                         ` Bart Van Assche
2023-01-31  2:49                                         ` Martin K. Petersen
2023-01-31  3:10                                           ` Damien Le Moal
2023-01-30 19:13                                       ` Bart Van Assche
2023-01-31  2:58                                         ` Martin K. Petersen
2023-01-31  3:03                                           ` Damien Le Moal
2023-01-25 23:11               ` Keith Busch
2023-01-26  0:08                 ` Damien Le Moal
2023-01-26  5:26                 ` Christoph Hellwig
2023-01-25  6:33         ` Christoph Hellwig
2023-01-27 12:43   ` Hannes Reinecke
2023-01-24 19:02 ` [PATCH v3 02/18] block: introduce BLK_STS_DURATION_LIMIT Niklas Cassel
2023-01-24 19:29   ` Bart Van Assche
2023-01-24 19:59     ` Keith Busch
2023-01-24 20:32       ` Bart Van Assche
2023-01-24 21:39         ` Damien Le Moal
2023-01-24 21:36       ` Damien Le Moal
2023-01-24 21:34     ` Damien Le Moal
2023-01-24 19:02 ` [PATCH v3 03/18] scsi: core: allow libata to complete successful commands via EH Niklas Cassel
2023-01-24 19:02 ` [PATCH v3 04/18] scsi: rename and move get_scsi_ml_byte() Niklas Cassel
2023-01-24 19:32   ` Bart Van Assche
2023-01-24 19:02 ` [PATCH v3 05/18] scsi: support retrieving sub-pages of mode pages Niklas Cassel
2023-01-24 19:34   ` Bart Van Assche
2023-01-24 19:02 ` [PATCH v3 06/18] scsi: support service action in scsi_report_opcode() Niklas Cassel
2023-01-24 19:36   ` Bart Van Assche
2023-01-24 19:02 ` [PATCH v3 07/18] scsi: sd: detect support for command duration limits Niklas Cassel
2023-01-24 19:39   ` Bart Van Assche
2023-01-27 13:00   ` Hannes Reinecke
2023-01-28  0:51     ` Damien Le Moal
2023-01-28  2:52       ` Bart Van Assche
2023-01-29  2:05         ` Damien Le Moal
2023-01-24 19:02 ` [PATCH v3 08/18] scsi: sd: set read/write commands CDL index Niklas Cassel
2023-01-27 15:30   ` Hannes Reinecke
2023-01-28  0:03     ` Damien Le Moal
2023-01-30 18:13       ` Hannes Reinecke
2023-01-24 19:02 ` [PATCH v3 09/18] scsi: sd: handle read/write CDL timeout failures Niklas Cassel
2023-01-27 15:34   ` Hannes Reinecke
2023-01-28  0:06     ` Damien Le Moal
2023-02-03 16:49     ` Niklas Cassel
2023-01-24 19:02 ` [PATCH v3 10/18] ata: libata-scsi: remove unnecessary !cmd checks Niklas Cassel
2023-01-27 15:35   ` Hannes Reinecke
2023-01-24 19:02 ` [PATCH v3 11/18] ata: libata: change ata_eh_request_sense() to not set CHECK_CONDITION Niklas Cassel
2023-01-27 15:36   ` Hannes Reinecke
2023-01-24 19:02 ` [PATCH v3 12/18] ata: libata: detect support for command duration limits Niklas Cassel
2023-01-24 19:02 ` [PATCH v3 13/18] ata: libata-scsi: handle CDL bits in ata_scsiop_maint_in() Niklas Cassel
2023-01-27 15:37   ` Hannes Reinecke
2023-01-24 19:03 ` [PATCH v3 14/18] ata: libata-scsi: add support for CDL pages mode sense Niklas Cassel
2023-01-27 15:38   ` Hannes Reinecke
2023-01-24 19:03 ` [PATCH v3 15/18] ata: libata: add ATA feature control sub-page translation Niklas Cassel
2023-01-27 15:40   ` Hannes Reinecke
2023-01-24 19:03 ` [PATCH v3 16/18] ata: libata: set read/write commands CDL index Niklas Cassel
2023-01-27 15:41   ` Hannes Reinecke
2023-01-24 19:03 ` [PATCH v3 17/18] ata: libata: handle completion of CDL commands using policy 0xD Niklas Cassel
2023-01-27 15:43   ` Hannes Reinecke
2023-01-24 19:03 ` [PATCH v3 18/18] Documentation: sysfs-block-device: document command duration limits Niklas Cassel
2023-01-27 15:43   ` Hannes Reinecke

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=6329e4fb-536b-00da-b38c-b6cb95f68994@opensource.wdc.com \
    --to=damien.lemoal@opensource.wdc.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-ide@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=niklas.cassel@wdc.com \
    --cc=paolo.valente@linaro.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