public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: [email protected]
Cc: Jens Axboe <[email protected]>, [email protected]
Subject: [PATCHSET REBASE 09/10] io_uring: optimise non-timeout waiting
Date: Thu,  5 Jan 2023 11:22:28 +0000	[thread overview]
Message-ID: <89f880574eceee6f4899783377ead234df7b3d04.1672916894.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>

Unlike the jiffy scheduling version, schedule_hrtimeout() jumps a few
functions before getting into schedule() even if there is no actual
timeout needed. Some tests showed that it takes up to 1% of CPU cycles.

Signed-off-by: Pavel Begunkov <[email protected]>
---
 io_uring/io_uring.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 54ec0106ab83..420b022f6c31 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2476,7 +2476,9 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 		return -EINTR;
 	if (unlikely(io_should_wake(iowq)))
 		return 0;
-	if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
+	if (*timeout == KTIME_MAX)
+		schedule();
+	else if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
 		return -ETIME;
 	return 0;
 }
-- 
2.38.1


  parent reply	other threads:[~2023-01-05 11:23 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-05 11:22 [PATCHSET REBASE 00/10] cq wait refactoring rebase Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 01/10] io_uring: rearrange defer list checks Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 02/10] io_uring: don't iterate cq wait fast path Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 03/10] io_uring: kill io_run_task_work_ctx Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 04/10] io_uring: move defer tw task checks Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 05/10] io_uring: parse check_cq out of wq waiting Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 06/10] io_uring: mimimise io_cqring_wait_schedule Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 07/10] io_uring: simplify io_has_work Pavel Begunkov
2023-01-05 11:22 ` [PATCHSET REBASE 08/10] io_uring: set TASK_RUNNING right after schedule Pavel Begunkov
2023-01-05 11:22 ` Pavel Begunkov [this message]
2023-01-05 11:22 ` [PATCHSET REBASE 10/10] io_uring: keep timeout in io_wait_queue Pavel Begunkov
2023-01-05 15:28 ` [PATCHSET REBASE 00/10] cq wait refactoring rebase Jens Axboe

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=89f880574eceee6f4899783377ead234df7b3d04.1672916894.git.asml.silence@gmail.com \
    [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