archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <>
To: "Carter Li 李通洲" <>,
	"Pavel Begunkov" <>
Cc: io-uring <>
Subject: Re: [RFC] single cqe per link
Date: Mon, 24 Feb 2020 20:13:12 -0700	[thread overview]
Message-ID: <> (raw)
In-Reply-To: <>

On 2/24/20 7:36 PM, Jens Axboe wrote:
> On 2/24/20 7:14 PM, Carter Li 李通洲 wrote:
>>> 2020年2月25日 上午8:39,Pavel Begunkov <> 写道:
>>> I've got curious about performance of the idea of having only 1 CQE per link
>>> (for the failed or last one). Tested it with a quick dirty patch doing
>>> submit-and-reap of a nops-link (patched for inline execution).
>>> 1) link size: 100
>>> old: 206 ns per nop
>>> new: 144 ns per nop
>>> 2) link size: 10
>>> old: 234 ns per nop
>>> new: 181 ns per nop
>>> 3) link size: 10, FORCE_ASYNC
>>> old: 667 ns per nop
>>> new: 569 ns per nop
>>> The patch below breaks sequences, linked_timeout and who knows what else.
>>> The first one requires synchronisation/atomic, so it's a bit in the way. I've
>>> been wondering, whether IOSQE_IO_DRAIN is popular and how much it's used. We can
>>> try to find tradeoff or even disable it with this feature.
>> Hello Pavel,
>> I still think flags tagged on sqes could be a better choice, which
>> gives users an ability to deside if they want to ignore the cqes, not
>> only for links, but also for normal sqes.
>> In addition, boxed cqes couldn’t resolve the issue of
> I would tend to agree, and it'd be trivial to just set the flag on
> whatever SQEs in the chain you don't care about. Or even an individual
> SQE, though that's probably a bit more of a reach in terms of use case.
> Maybe nop with drain + ignore?
> In any case it's definitely more flexible.

In the interest of taking this to the extreme, I tried a nop benchmark
on my laptop (qemu/kvm). Granted, this setup is particularly sensitive
to spinlocks, they are a lot more expensive there than on a real host.

Anyway, regular nops run at about 9.5M/sec with a single thread.
Flagging all SQEs with IOSQE_NO_CQE nets me about 14M/sec. So a handy
improvement. Looking at the top of profiles:


+   28.45%  io_uring  [kernel.kallsyms]  [k] _raw_spin_unlock_irqrestore
+   14.38%  io_uring  [kernel.kallsyms]  [k] io_submit_sqes
+    9.38%  io_uring  [kernel.kallsyms]  [k] io_put_req
+    7.25%  io_uring       [.] syscall
+    6.12%  io_uring  [kernel.kallsyms]  [k] kmem_cache_free


+   19.72%  io_uring  [kernel.kallsyms]  [k] io_put_req
+   11.93%  io_uring  [kernel.kallsyms]  [k] io_submit_sqes
+   10.14%  io_uring  [kernel.kallsyms]  [k] kmem_cache_free
+    9.55%  io_uring       [.] syscall
+    7.48%  io_uring  [kernel.kallsyms]  [k] __io_queue_sqe

I'll try the real disk IO tomorrow, using polled IO.

Jens Axboe

  reply	other threads:[~2020-02-25  3:13 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-25  0:39 [RFC] single cqe per link Pavel Begunkov
2020-02-25  2:14 ` Carter Li 李通洲
2020-02-25  2:36   ` Jens Axboe
2020-02-25  3:13     ` Jens Axboe [this message]
2020-02-25 10:12       ` Pavel Begunkov
2020-02-25 20:20         ` Jens Axboe
2020-02-25 21:13           ` Pavel Begunkov
2020-08-21  5:17             ` Questions about IORING_OP_ASYNC_CANCEL usage Carter Li 李通洲
2020-08-21  5:20               ` Carter Li 李通洲
2020-02-25  2:24 ` [RFC] single cqe per link 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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \ \ \

* 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;
as well as URLs for NNTP newsgroup(s).