From: Tejun Heo <tj@kernel.org>
To: yi sun <sunyibuaa@gmail.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>,
Yi Sun <yi.sun@unisoc.com>,
jiangshanlai@gmail.com, jaegeuk@kernel.org, chao@kernel.org,
ebiggers@google.com, linux-f2fs-devel@lists.sourceforge.net,
linux-kernel@vger.kernel.org, niuzhiguo84@gmail.com,
Hao_hao.Wang@unisoc.com, yunlongxing23@gmail.com
Subject: Re: [PATCH v2 1/2] workqueue: new struct io_work
Date: Tue, 2 Jul 2024 06:40:25 -1000 [thread overview]
Message-ID: <ZoQtef_6xfd4FAwe@slm.duckdns.org> (raw)
In-Reply-To: <CALpufv3bAsMey1DFb8HPbp8gPZWBU-6rrhvRWwVQsxXhPXOvdA@mail.gmail.com>
Hello,
On Tue, Jul 02, 2024 at 05:27:19PM +0800, yi sun wrote:
> Yes, adding the io priority attribute to work will bring huge benefits in the
> following scenarios:
> The system has huge IO pressure (these IOs may all be low-priority IOs),
> and a work (we hope to complete quickly) is also doing IO. If this work
> does not set IO priority, it will be blocked because it is difficult to get IO
> resources. And if this work sets a high IO priority and passes the IO priority
> to kworker, then this work will be completed quickly (as we expect).
As I wrote previously, you can still get trapped in a pretty bad priority
inversion whether from workqueue concurrency or queue depth exhaustion. I'm
sure that there's some spectrum of contention conditions that can be helped
with just setting ioprio, but it's a pretty partial solution.
Thanks.
--
tejun
next prev parent reply other threads:[~2024-07-02 16:40 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-07-01 7:51 [PATCH v2 0/2] new struct io_work and use it in f2fs fsverity work Yi Sun
2024-07-01 7:51 ` [PATCH v2 1/2] workqueue: new struct io_work Yi Sun
2024-07-01 17:32 ` Tejun Heo
2024-07-02 3:53 ` Kent Overstreet
2024-07-02 9:27 ` yi sun
2024-07-02 16:40 ` Tejun Heo [this message]
2024-07-02 16:45 ` Kent Overstreet
2024-07-02 3:40 ` kernel test robot
2024-07-02 21:51 ` kernel test robot
2024-07-01 7:51 ` [PATCH v2 2/2] f2fs: set io priority for fsverity work Yi Sun
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=ZoQtef_6xfd4FAwe@slm.duckdns.org \
--to=tj@kernel.org \
--cc=Hao_hao.Wang@unisoc.com \
--cc=chao@kernel.org \
--cc=ebiggers@google.com \
--cc=jaegeuk@kernel.org \
--cc=jiangshanlai@gmail.com \
--cc=kent.overstreet@linux.dev \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=niuzhiguo84@gmail.com \
--cc=sunyibuaa@gmail.com \
--cc=yi.sun@unisoc.com \
--cc=yunlongxing23@gmail.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
all inboxes | Powered by JetHome®