From: Jens Axboe <[email protected]>
To: Pavel Begunkov <[email protected]>, [email protected]
Subject: Re: [PATCH for-next 5/7] io_uring: remove ->flush_cqes optimisation
Date: Sun, 19 Jun 2022 09:52:40 -0600 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 6/19/22 8:52 AM, Pavel Begunkov wrote:
> On 6/19/22 14:31, Jens Axboe wrote:
>> On 6/19/22 5:26 AM, Pavel Begunkov wrote:
>>> It's not clear how widely used IOSQE_CQE_SKIP_SUCCESS is, and how often
>>> ->flush_cqes flag prevents from completion being flushed. Sometimes it's
>>> high level of concurrency that enables it at least for one CQE, but
>>> sometimes it doesn't save much because nobody waiting on the CQ.
>>>
>>> Remove ->flush_cqes flag and the optimisation, it should benefit the
>>> normal use case. Note, that there is no spurious eventfd problem with
>>> that as checks for spuriousness were incorporated into
>>> io_eventfd_signal().
>>
>> Would be note to quantify, which should be pretty easy. Eg run a nop
>> workload, then run the same but with CQE_SKIP_SUCCESS set. That'd take
>> it to the extreme, and I do think it'd be nice to have an understanding
>> of how big the gap could potentially be.
>>
>> With luck, it doesn't really matter. Always nice to kill stuff like
>> this, if it isn't that impactful.
>
> Trying without this patch nops32 (submit 32 nops, complete all, repeat).
>
> 1) all CQE_SKIP:
> ~51 Mreqs/s
> 2) all CQE_SKIP but last, so it triggers locking + *ev_posted()
> ~49 Mreq/s
> 3) same as 2) but another task waits on CQ (so we call wake_up_all)
> ~36 Mreq/s
>
> And that's more or less expected. What is more interesting for me
> is how often for those using CQE_SKIP it helps to avoid this
> ev_posted()/etc. They obviously can't just mark all requests
> with it, and most probably helping only some quite niche cases.
That's not too bad. But I think we disagree on CQE_SKIP being niche,
there are several standard cases where it makes sense. Provide buffers
is one, though that one we have a better solution for now. But also eg
OP_CLOSE is something that I'd personally use CQE_SKIP with always.
Hence I don't think it's fair or reasonable to call it "quite niche" in
terms of general usability.
But if this helps in terms of SINGLE_ISSUER, then I think it's worth it
as we'll likely see more broad appeal from that.
--
Jens Axboe
next prev parent reply other threads:[~2022-06-19 15:52 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-19 11:26 [PATCH for-next 0/7] cqe posting cleanups Pavel Begunkov
2022-06-19 11:26 ` [PATCH for-next 1/7] io_uring: remove extra io_commit_cqring() Pavel Begunkov
2022-06-19 11:26 ` [PATCH for-next 2/7] io_uring: reshuffle io_uring/io_uring.h Pavel Begunkov
2022-06-19 11:26 ` [PATCH for-next 3/7] io_uring: move io_eventfd_signal() Pavel Begunkov
2022-06-19 11:26 ` [PATCH for-next 4/7] io_uring: hide eventfd assumptions in evenfd paths Pavel Begunkov
2022-06-19 18:18 ` Jens Axboe
2022-06-19 18:49 ` Pavel Begunkov
2022-06-19 18:58 ` Jens Axboe
2022-06-19 11:26 ` [PATCH for-next 5/7] io_uring: remove ->flush_cqes optimisation Pavel Begunkov
2022-06-19 13:31 ` Jens Axboe
2022-06-19 14:52 ` Pavel Begunkov
2022-06-19 15:52 ` Jens Axboe [this message]
2022-06-19 16:15 ` Pavel Begunkov
2022-06-19 16:17 ` Jens Axboe
2022-06-19 16:19 ` Pavel Begunkov
2022-06-19 16:38 ` Jens Axboe
2022-06-19 16:38 ` Jens Axboe
2022-06-19 11:26 ` [PATCH for-next 6/7] io_uring: introduce locking helpers for CQE posting Pavel Begunkov
2022-06-19 13:30 ` Jens Axboe
2022-06-19 14:20 ` Pavel Begunkov
2022-06-19 15:50 ` Jens Axboe
2022-06-19 11:26 ` [PATCH for-next 7/7] io_uring: add io_commit_cqring_flush() Pavel Begunkov
2022-06-19 12:36 ` [PATCH for-next 0/7] cqe posting cleanups Pavel Begunkov
2022-06-19 16:01 ` 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 \
[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