public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: [email protected]
Subject: [PATCHSET for-next 0/8] io_uring SQPOLL improvements
Date: Wed,  2 Sep 2020 20:20:45 -0600	[thread overview]
Message-ID: <[email protected]> (raw)

The SQPOLL support is useful as it stands, but for various use cases
it's less useful than it could be. In no particular order:

- We currently require root. I'd like to "relax" that to CAP_SYS_NICE
  instead, which I think fits quite nicely with it.

- You get one poll thread per ring. For cases that use multiple rings,
  this isn't necessary and is also quite wasteful.

Patch 1 is a cleanup, patch 2 allows CAP_SYS_NICE for SQPOLL, and the
remaining patches gradually work our way to be able to support
shared SQPOLL threads. The latter works exactly like
IORING_SETUP_ATTACH_WQ, where we currently support just sharing the
io-wq backend between threads. With this added, we also support the
SQPOLL thread.

I'm sure there are some quirks and issues to iron out in the SQPOLL
series, but some initial testing shows it working for me and it passes
the test suite. I'll run some more testing, reviews would be more than
welcome.

 fs/io_uring.c | 385 +++++++++++++++++++++++++++++++++++---------------
 1 file changed, 268 insertions(+), 117 deletions(-)

-- 
Jens Axboe



             reply	other threads:[~2020-09-03  2:21 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-03  2:20 Jens Axboe [this message]
2020-09-03  2:20 ` [PATCH 1/8] io_uring: io_sq_thread() doesn't need to flush signals Jens Axboe
2020-09-03  2:20 ` [PATCH 2/8] io_uring: allow SQPOLL with CAP_SYS_NICE privileges Jens Axboe
2020-09-03  2:20 ` [PATCH 3/8] io_uring: use private ctx wait queue entries for SQPOLL Jens Axboe
2020-09-03  2:20 ` [PATCH 4/8] io_uring: move SQPOLL post-wakeup ring need wakeup flag into wake handler Jens Axboe
2020-09-03  2:20 ` [PATCH 5/8] io_uring: split work handling part of SQPOLL into helper Jens Axboe
2020-09-03  2:20 ` [PATCH 6/8] io_uring: split SQPOLL data into separate structure Jens Axboe
2020-09-03  2:20 ` [PATCH 7/8] io_uring: base SQPOLL handling off io_sq_data Jens Axboe
2020-09-03  2:20 ` [PATCH 8/8] io_uring: enable IORING_SETUP_ATTACH_WQ to attach to SQPOLL thread too Jens Axboe
2020-09-07  8:56   ` Xiaoguang Wang
2020-09-07 14:00     ` Pavel Begunkov
2020-09-07 16:11       ` Jens Axboe
2020-09-07 16:14     ` Jens Axboe
2020-09-07 16:18       ` Jens Axboe
2020-09-08  2:28         ` Xiaoguang Wang
2020-09-08  2:53       ` Xiaoguang Wang

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    /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