io-uring.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Colin Walters <walters@verbum.org>,
	Stefan Metzmacher <metze@samba.org>,
	io-uring@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Subject: Re: [PATCHSET v2 0/6] io_uring: add support for open/close
Date: Thu, 16 Jan 2020 17:51:40 -0700	[thread overview]
Message-ID: <18c5a50e-cd7b-cb7f-c159-322486550e8f@kernel.dk> (raw)
In-Reply-To: <1e8a9e98-67f8-4e2f-8185-040b9979bc1a@www.fastmail.com>

On 1/16/20 5:44 PM, Colin Walters wrote:
> 
> 
> On Thu, Jan 16, 2020, at 5:50 PM, Stefan Metzmacher wrote:
>>
>> The client can compound a chain with open, getinfo, read, close
>> getinfo, read and close get an file handle of -1 and implicitly
>> get the fd generated/used in the previous request.
> 
> Sounds similar to  https://capnproto.org/rpc.html too.

Never heard of it, but I don't see how you can do any of this in an
efficient manner without kernel support. Unless it's just wrapping the
communication in its own protocol and using that as the basis for the
on-wire part. It has "infinitely faster" in a yellow sticker, so it must
work :-)

> But that seems most valuable in a situation with nontrivial latency.

Which is basically what Stefan is looking at, over the network open,
read, close etc is pretty nondeterministic. But even for local storage,
being able to setup a bundle like that and have it automagically work
makes for easier programming and more efficient communication with the
kernel.


-- 
Jens Axboe


  reply	other threads:[~2020-01-17  0:51 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-07 17:00 [PATCHSET v2 0/6] io_uring: add support for open/close Jens Axboe
2020-01-07 17:00 ` [PATCH 1/6] fs: add namei support for doing a non-blocking path lookup Jens Axboe
2020-01-25 13:15   ` Jeff Layton
2020-01-07 17:00 ` [PATCH 2/6] fs: make build_open_flags() available internally Jens Axboe
2020-01-07 17:00 ` [PATCH 3/6] io_uring: add support for IORING_OP_OPENAT Jens Axboe
2020-01-08 13:05   ` Stefan Metzmacher
2020-01-08 16:20     ` Jens Axboe
2020-01-08 16:32       ` Stefan Metzmacher
2020-01-08 16:40         ` Jens Axboe
2020-01-08 17:04           ` Stefan Metzmacher
2020-01-08 22:53             ` Jens Axboe
2020-01-08 23:03               ` Stefan Metzmacher
2020-01-08 23:05                 ` Jens Axboe
2020-01-08 23:11                   ` Stefan Metzmacher
2020-01-08 23:22                     ` Jens Axboe
2020-01-09 10:40                       ` Stefan Metzmacher
2020-01-09 21:31                         ` Jens Axboe
2020-01-16 22:42                           ` Stefan Metzmacher
2020-01-17  0:16                             ` Jens Axboe
2020-01-07 17:00 ` [PATCH 4/6] fs: move filp_close() outside of __close_fd_get_file() Jens Axboe
2020-01-07 17:00 ` [PATCH 5/6] io-wq: add support for uncancellable work Jens Axboe
2020-01-07 17:00 ` [PATCH 6/6] io_uring: add support for IORING_OP_CLOSE Jens Axboe
2020-01-08 21:17 ` [PATCHSET v2 0/6] io_uring: add support for open/close Stefan Metzmacher
2020-01-08 22:57   ` Jens Axboe
2020-01-08 23:05     ` Stefan Metzmacher
2020-01-09  1:02       ` Jens Axboe
2020-01-09  2:03         ` Jens Axboe
2020-01-16 22:50           ` Stefan Metzmacher
2020-01-17  0:18             ` Jens Axboe
2020-01-20 12:15               ` Stefan Metzmacher
2020-01-20 13:04                 ` Pavel Begunkov
2020-01-17  0:44             ` Colin Walters
2020-01-17  0:51               ` Jens Axboe [this message]
2020-01-17  9:32               ` Pavel Begunkov
2020-01-17 15:21                 ` Jens Axboe
2020-01-17 22:27                   ` Pavel Begunkov
2020-01-17 22:36                     ` 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=18c5a50e-cd7b-cb7f-c159-322486550e8f@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=metze@samba.org \
    --cc=walters@verbum.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 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).