From: Christoph Hellwig <hch@lst.de>
To: Damien Le Moal <dlemoal@kernel.org>
Cc: Bart Van Assche <bvanassche@acm.org>,
Christoph Hellwig <hch@lst.de>, 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: Thu, 14 Dec 2023 09:51:59 +0100 [thread overview]
Message-ID: <20231214085159.GA9006@lst.de> (raw)
In-Reply-To: <abc13a22-74b4-4f72-b592-09781d0cfdd2@kernel.org>
On Thu, Dec 14, 2023 at 09:37:21AM +0900, Damien Le Moal wrote:
> Yes, that can be trivially done with the sd_zbc.c zone append emulation. If you
> check the code, you'll see that sd_zbc_prepare_zone_append() returns
> BLK_STS_ZONE_RESOURCE if the target zone is already locked. That causes a
> requeue and the zone append to be resubmitted later. All you need to do for UFS
> devices is tweak that to not requeue the zone append if the write command used
> to emulate it can be issued. The completion path will also, of course, need some
> tweaks to not attempt to unlock the target zone if it was not locked.
On the Linux side yes. I still don't see how the hardware can actually
make this scheme work withou the potential of deadlocks. But compared
to the problems with having a completely in-order I/O stacks that's
peanuts as they say in Germany.
prev parent reply other threads:[~2023-12-14 8:52 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
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 [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=20231214085159.GA9006@lst.de \
--to=hch@lst.de \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=dlemoal@kernel.org \
--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 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.