public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: Miklos Szeredi <[email protected]>
Cc: [email protected]
Subject: Re: io_uring_prep_openat_direct() and link/drain
Date: Tue, 5 Apr 2022 08:44:01 -0600	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <CAJfpeguWv7kJn2RReTp0Hfv8hCoAbGSjGmRyNGQnPcU2exrewQ@mail.gmail.com>

On 4/5/22 1:45 AM, Miklos Szeredi wrote:
> On Sat, 2 Apr 2022 at 03:17, Jens Axboe <[email protected]> wrote:
>>
>> On 4/1/22 10:21 AM, Jens Axboe wrote:
>>> On 4/1/22 10:02 AM, Miklos Szeredi wrote:
>>>> On Fri, 1 Apr 2022 at 17:36, Jens Axboe <[email protected]> wrote:
>>>>
>>>>> I take it you're continually reusing those slots?
>>>>
>>>> Yes.
>>>>
>>>>>  If you have a test
>>>>> case that'd be ideal. Agree that it sounds like we just need an
>>>>> appropriate breather to allow fput/task_work to run. Or it could be the
>>>>> deferral free of the fixed slot.
>>>>
>>>> Adding a breather could make the worst case latency be large.  I think
>>>> doing the fput synchronously would be better in general.
>>>
>>> fput() isn't sync, it'll just offload to task_work. There are some
>>> dependencies there that would need to be checked. But we'll find a way
>>> to deal with it.
>>>
>>>> I test this on an VM with 8G of memory and run the following:
>>>>
>>>> ./forkbomb 14 &
>>>> # wait till 16k processes are forked
>>>> for i in `seq 1 100`; do ./procreads u; done
>>>>
>>>> You can compare performance with plain reads (./procreads p), the
>>>> other tests don't work on public kernels.
>>>
>>> OK, I'll check up on this, but probably won't have time to do so before
>>> early next week.
>>
>> Can you try with this patch? It's not complete yet, there's actually a
>> bunch of things we can do to improve the direct descriptor case. But
>> this one is easy enough to pull off, and I think it'll fix your OOM
>> case. Not a proposed patch, but it'll prove the theory.
> 
> Sorry for the delay..
> 
> Patch works like charm.

OK good, then it is the issue I suspected. Thanks for testing!

-- 
Jens Axboe


  reply	other threads:[~2022-04-06  2:23 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-03-29 13:20 io_uring_prep_openat_direct() and link/drain Miklos Szeredi
2022-03-29 16:08 ` Jens Axboe
2022-03-29 17:04   ` Jens Axboe
2022-03-29 18:21     ` Miklos Szeredi
2022-03-29 18:26       ` Jens Axboe
2022-03-29 18:31         ` Miklos Szeredi
2022-03-29 18:40           ` Jens Axboe
2022-03-29 19:30             ` Miklos Szeredi
2022-03-29 20:03               ` Jens Axboe
2022-03-30  8:18                 ` Miklos Szeredi
2022-03-30 12:35                   ` Jens Axboe
2022-03-30 12:43                     ` Miklos Szeredi
2022-03-30 12:48                       ` Jens Axboe
2022-03-30 12:51                         ` Miklos Szeredi
2022-03-30 14:58                           ` Miklos Szeredi
2022-03-30 15:05                             ` Jens Axboe
2022-03-30 15:12                               ` Miklos Szeredi
2022-03-30 15:17                                 ` Jens Axboe
2022-03-30 15:53                                   ` Jens Axboe
2022-03-30 17:49                                     ` Jens Axboe
2022-04-01  8:40                                       ` Miklos Szeredi
2022-04-01 15:36                                         ` Jens Axboe
2022-04-01 16:02                                           ` Miklos Szeredi
2022-04-01 16:21                                             ` Jens Axboe
2022-04-02  1:17                                               ` Jens Axboe
2022-04-05  7:45                                                 ` Miklos Szeredi
2022-04-05 14:44                                                   ` Jens Axboe [this message]
2022-04-21 12:31                                                     ` Miklos Szeredi
2022-04-21 12:34                                                       ` Jens Axboe
2022-04-21 12:39                                                         ` Miklos Szeredi
2022-04-21 12:41                                                           ` Jens Axboe
2022-04-21 13:10                                                             ` Miklos Szeredi

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