public inbox for [email protected]
 help / color / mirror / Atom feed
From: Ming Lei <[email protected]>
To: Jens Axboe <[email protected]>
Cc: [email protected], Guang Wu <[email protected]>,
	[email protected]
Subject: Re: [v6.4 Regression] rust/io_uring: tests::net::test_tcp_recv_multi hangs
Date: Thu, 19 Oct 2023 19:47:10 +0800	[thread overview]
Message-ID: <ZTEXPlB70Eqe3WOJ@fedora> (raw)
In-Reply-To: <[email protected]>

On Thu, Oct 19, 2023 at 05:31:11AM -0600, Jens Axboe wrote:
> On 10/19/23 2:06 AM, Ming Lei wrote:
> > Hello Jens,
> > 
> > Guang Wu found that tests::net::test_tcp_recv_multi in rust:io_uring
> > hangs, and no such issue in RH test kernel.
> > 
> > - git clone https://github.com/tokio-rs/io-uring.git
> > - cd io-uring
> > - cargo run --package io-uring-test
> > 
> > I figured out that it is made by missing the last CQE with -ENOBUFS,
> > which is caused by commit a2741c58ac67 ("io_uring/net: don't retry recvmsg()
> > unnecessarily").
> > 
> > I am not sure if the last CQE should be returned and that depends how normal
> > recv_multi is written, but IORING_CQE_F_MORE in the previous CQE shouldn't be
> > returned at least.
> 
> Is this because it depends on this spurious retry? IOW, it adds N
> buffers and triggers N receives, then depends on an internal extra retry
> which would then yield -ENOBUFS? Because that sounds like a broken test.

Yeah, that is basically what the test does. 

The test gets two recv CQEs, both have IORING_CQE_F_MORE. And it waits for 3
CQEs, and never return because there isn't the 3rd CQE after
a2741c58ac67 ("io_uring/net: don't retry recvmsg() unnecessarily")
is merged.

> As long as the recv triggers successfully, IORING_CQE_F_MORE will be
> set. Only if it his some terminating condition would it trigger a CQE
> without the MORE flag set. If it remains armed and ready to trigger
> again, it will have MORE set. I'll take a look, this is pure guesswork
> on my side right now.

.B IORING_CQE_F_MORE
If set, the application should expect more completions from the request. This
is used for requests that can generate multiple completions, such as multi-shot
requests, receive, or accept.

I understand that if one CQE is received with IORING_CQE_F_MORE, it is
reasonable for userspace to wait for one extra CQE, is this expectation
correct? Or the documentation needs to be updated?


Thanks,
Ming


  reply	other threads:[~2023-10-19 11:48 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-19  8:06 [v6.4 Regression] rust/io_uring: tests::net::test_tcp_recv_multi hangs Ming Lei
2023-10-19 11:31 ` Jens Axboe
2023-10-19 11:47   ` Ming Lei [this message]
2023-10-19 12:10     ` 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=ZTEXPlB70Eqe3WOJ@fedora \
    [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