From: Keith Busch <kbusch@kernel.org>
To: Matt Fleming <mfleming@cloudflare.com>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
kernel-team <kernel-team@cloudflare.com>
Subject: Re: 10x I/O await times in 6.12
Date: Mon, 21 Apr 2025 09:22:40 -0600 [thread overview]
Message-ID: <aAZiwGy1A7J4spDk@kbusch-mbp.dhcp.thefacebook.com> (raw)
In-Reply-To: <CAGis_TVSAPjYwVjUyur0_NFsDi9jmJ_oWhBHrJ-bEknG-nJO9Q@mail.gmail.com>
On Mon, Apr 21, 2025 at 09:53:10AM +0100, Matt Fleming wrote:
> Hey there,
>
> We're moving to 6.12 at Cloudflare and noticed that write await times
> in iostat are 10x what they were in 6.6. After a bit of bpftracing
> (script to find all plug times above 10ms below), it seems like this
> is an accounting error caused by the plug->cur_ktime optimisation
> rather than anything more material.
>
> It appears as though a task can enter __submit_bio() with ->plug set
> and a very stale cur_ktime value on the order of milliseconds. Is this
> expected behaviour? It looks like it leads to inaccurate I/O times.
There are places with a block plug that call cond_resched(), which
doesn't invalidate the plug's cached ktime. You could end up with a
stale ktime if your process is scheduled out.
next prev parent reply other threads:[~2025-04-21 15:22 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-21 8:53 10x I/O await times in 6.12 Matt Fleming
2025-04-21 12:21 ` Yu Kuai
2025-04-23 10:51 ` Matt Fleming
2025-04-24 2:35 ` Yu Kuai
2025-05-01 9:52 ` Matt Fleming
2026-04-23 18:18 ` Matt Fleming
2025-04-21 15:22 ` Keith Busch [this message]
2025-04-21 18:35 ` Matt Fleming
2025-04-21 18:53 ` Keith Busch
2025-04-21 19:10 ` Matt Fleming
2025-04-22 1:39 ` Yu Kuai
2025-04-22 1:28 ` Yu Kuai
2025-04-22 1:39 ` Keith Busch
2025-04-22 3:02 ` Yu Kuai
2025-04-22 10:45 ` Matt Fleming
2025-04-23 3:36 ` Yu Kuai
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=aAZiwGy1A7J4spDk@kbusch-mbp.dhcp.thefacebook.com \
--to=kbusch@kernel.org \
--cc=axboe@kernel.dk \
--cc=kernel-team@cloudflare.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mfleming@cloudflare.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