From: Christoph Hellwig <hch@lst.de>
To: Bart Van Assche <bvanassche@acm.org>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
Jaegeuk Kim <jaegeuk@kernel.org>,
Damien Le Moal <dlemoal@kernel.org>
Subject: Re: [PATCH 3/3] block/mq-deadline: Disable I/O prioritization in certain cases
Date: Mon, 11 Dec 2023 17:57:20 +0100 [thread overview]
Message-ID: <20231211165720.GC26039@lst.de> (raw)
In-Reply-To: <20231205053213.522772-4-bvanassche@acm.org>
On Mon, Dec 04, 2023 at 09:32:13PM -0800, Bart Van Assche wrote:
> Fix the following two issues:
> - Even with prio_aging_expire set to zero, I/O priorities still affect the
> request order.
> - Assigning I/O priorities with the ioprio cgroup policy breaks zoned
> storage support in the mq-deadline scheduler.
Not it doesn't, how would it? Or do you mean your f2fs hacks where you
assume there is some order kept? You really need to get rid of them
and make sure f2fs doesn't care about reordering by writing the
metadata that records the data location only at I/O completion time.
Not only does that make zoned I/O trivially right, it also fixes the
stale data exposures you are almost guaranteed to have even on
conventional devices without that.
next prev parent reply other threads:[~2023-12-11 16:57 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 [this message]
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
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=20231211165720.GC26039@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 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).