From: Bart Van Assche <bvanassche@acm.org>
To: Christoph Hellwig <hch@lst.de>
Cc: Damien Le Moal <dlemoal@kernel.org>, Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, Jaegeuk Kim <jaegeuk@kernel.org>
Subject: Re: [PATCH 3/3] block/mq-deadline: Disable I/O prioritization in certain cases
Date: Tue, 12 Dec 2023 09:42:24 -0800 [thread overview]
Message-ID: <686cc853-96e2-4aa4-8f68-fdcc5cdabbba@acm.org> (raw)
In-Reply-To: <20231212171846.GA28682@lst.de>
On 12/12/23 09:18, Christoph Hellwig wrote:
> On Tue, Dec 12, 2023 at 09:15:48AM -0800, Bart Van Assche wrote:
>> As mentioned before, UFS devices implement the SCSI command set and hence do not
>> support write append operations. If anyone else standardizes a write append
>> command for SCSI we can ask UFS vendors to implement that command. However, as
>> far as I know nobody in T10 is working on standardizing a write append command.
>
> The actual hardware support does not matter, it's the programming model.
> Even with the zone append emulation in sd you don't need to care about
> reordering due to I/O priorities.
The actual hardware support does matter. Using the zone append emulation from
drivers/scsi/sd_zbc.c (or any other zone append emulation) is not an option for
high performance devices. This is because emulating zone append can only be done
by serializing write operations. Any such serialization negatively affects
performance.
Thanks,
Bart.
next prev parent reply other threads:[~2023-12-12 17:42 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-05 5:32 [PATCH 0/3] Improve mq-deadline I/O priority support Bart Van Assche
2023-12-05 5:32 ` [PATCH 1/3] block/mq-deadline: Use dd_rq_ioclass() instead of open-coding it Bart Van Assche
2023-12-06 2:35 ` Damien Le Moal
2023-12-11 16:54 ` Christoph Hellwig
2023-12-05 5:32 ` [PATCH 2/3] block/mq-deadline: Introduce dd_bio_ioclass() Bart Van Assche
2023-12-06 2:35 ` Damien Le Moal
2023-12-11 16:55 ` Christoph Hellwig
2023-12-18 17:35 ` Bart Van Assche
2023-12-05 5:32 ` [PATCH 3/3] block/mq-deadline: Disable I/O prioritization in certain cases Bart Van Assche
2023-12-06 2:42 ` Damien Le Moal
2023-12-06 3:24 ` Bart Van Assche
2023-12-08 0:03 ` Bart Van Assche
2023-12-08 3:37 ` Damien Le Moal
2023-12-08 18:40 ` Bart Van Assche
2023-12-11 7:40 ` Damien Le Moal
2023-12-12 22:44 ` Bart Van Assche
2023-12-12 23:52 ` Damien Le Moal
2023-12-13 1:02 ` Bart Van Assche
2023-12-13 5:29 ` Damien Le Moal
2023-12-11 16:57 ` Christoph Hellwig
2023-12-11 17:20 ` Bart Van Assche
2023-12-12 15:40 ` Christoph Hellwig
2023-12-11 22:40 ` Damien Le Moal
2023-12-12 15:41 ` Christoph Hellwig
2023-12-12 17:15 ` Bart Van Assche
2023-12-12 17:18 ` Christoph Hellwig
2023-12-12 17:42 ` Bart Van Assche [this message]
2023-12-12 17:48 ` Christoph Hellwig
2023-12-12 18:09 ` Bart Van Assche
2023-12-12 18:13 ` Christoph Hellwig
2023-12-12 18:19 ` Bart Van Assche
2023-12-12 18:26 ` Christoph Hellwig
2023-12-12 19:03 ` Jaegeuk Kim
2023-12-12 23:44 ` Damien Le Moal
2023-12-13 16:49 ` Jaegeuk Kim
2023-12-13 22:55 ` Damien Le Moal
2023-12-13 15:56 ` Christoph Hellwig
2023-12-13 16:41 ` Jaegeuk Kim
2023-12-14 8:57 ` Christoph Hellwig
2023-12-14 17:22 ` Jaegeuk Kim
2023-12-15 1:12 ` Damien Le Moal
2023-12-15 2:03 ` Jaegeuk Kim
2023-12-15 2:20 ` Keith Busch
2023-12-15 4:49 ` Christoph Hellwig
2023-12-14 19:32 ` Bart Van Assche
2023-12-14 0:08 ` Bart Van Assche
2023-12-14 0:37 ` Damien Le Moal
2023-12-14 8:51 ` 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=686cc853-96e2-4aa4-8f68-fdcc5cdabbba@acm.org \
--to=bvanassche@acm.org \
--cc=axboe@kernel.dk \
--cc=dlemoal@kernel.org \
--cc=hch@lst.de \
--cc=jaegeuk@kernel.org \
--cc=linux-block@vger.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;
as well as URLs for NNTP newsgroup(s).