From: Jens Axboe <[email protected]>
To: Xiaoguang Wang <[email protected]>,
[email protected]
Subject: Re: [PATCH 8/8] io_uring: enable IORING_SETUP_ATTACH_WQ to attach to SQPOLL thread too
Date: Mon, 7 Sep 2020 10:18:34 -0600 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 9/7/20 10:14 AM, Jens Axboe wrote:
> On 9/7/20 2:56 AM, Xiaoguang Wang wrote:
>> 3. When it's appropriate to set ctx's IORING_SQ_NEED_WAKEUP flag? In
>> your current implementation, if a ctx is marked as SQT_IDLE, this ctx
>> will be set IORING_SQ_NEED_WAKEUP flag, but if other ctxes have work
>> to do, then io_sq_thread is still running and does not need to be
>> waken up, then a later wakeup form userspace is unnecessary. I think
>> it maybe appropriate to set IORING_SQ_NEED_WAKEUP when all ctxes have
>> no work to do, you can have a look at my attached codes:)
>
> That's a good point, any chance I can get you to submit a patch to fix
> that up?
Something like this?
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 4bd18e01ae89..80913973337a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6747,8 +6747,6 @@ static enum sq_ret __io_sq_thread(struct io_ring_ctx *ctx,
goto again;
}
- io_ring_set_wakeup_flag(ctx);
-
to_submit = io_sqring_entries(ctx);
if (!to_submit || ret == -EBUSY)
return SQT_IDLE;
@@ -6825,6 +6823,8 @@ static int io_sq_thread(void *data)
io_run_task_work();
cond_resched();
} else if (ret == SQT_IDLE) {
+ list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
+ io_ring_set_wakeup_flag(ctx);
schedule();
start_jiffies = jiffies;
}
--
Jens Axboe
next prev parent reply other threads:[~2020-09-07 16:18 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-03 2:20 [PATCHSET for-next 0/8] io_uring SQPOLL improvements Jens Axboe
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 [this message]
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] \
[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