From: Jens Axboe <axboe@kernel.dk>
To: Pavel Begunkov <asml.silence@gmail.com>, io-uring@vger.kernel.org
Subject: Re: [PATCH v3 0/3] next work propagation
Date: Tue, 3 Mar 2020 11:57:50 -0700 [thread overview]
Message-ID: <1df4c652-31c1-2368-0520-440bfe29cfbd@kernel.dk> (raw)
In-Reply-To: <90a9fcda-dd44-1b5c-7dc6-28ec3a1dd81a@gmail.com>
On 3/3/20 11:52 AM, Pavel Begunkov wrote:
> On 03/03/2020 21:33, Pavel Begunkov wrote:
>> The next propagation bits are done similarly as it was before, but
>> - nxt stealing is now at top-level, but not hidden in handlers
>> - ensure there is no with REQ_F_DONT_STEAL_NEXT
>
> Forgot to update this part, and also add, that there is no
> refcount_dec_fetch(), so I did
>
> io_put_req_async_completion() {
> refcount_dec()
> refcount_read()
> }
>
> because checks in refcount*() are useful, and I intend to remove
> refcount_dec() with the optimisation patches.
I think that's fine, and it's likely still faster than a
refcount_dec_return() would be. Plus then we'd have to argue about that,
since it might not be safe for all use cases. For this one it is.
--
Jens Axboe
next prev parent reply other threads:[~2020-03-03 18:57 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-03 18:33 [PATCH v3 0/3] next work propagation Pavel Begunkov
2020-03-03 18:33 ` [PATCH v3 1/3] io_uring: make submission ref putting consistent Pavel Begunkov
2020-03-03 18:33 ` [PATCH v3 2/3] io_uring: remove @nxt from handlers Pavel Begunkov
2020-03-03 18:33 ` [PATCH v3 3/3] io_uring: get next work with submission ref drop Pavel Begunkov
2020-03-03 18:52 ` [PATCH v3 0/3] next work propagation Pavel Begunkov
2020-03-03 18:57 ` Jens Axboe [this message]
2020-03-03 21:40 ` 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=1df4c652-31c1-2368-0520-440bfe29cfbd@kernel.dk \
--to=axboe@kernel.dk \
--cc=asml.silence@gmail.com \
--cc=io-uring@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.