linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bernd Schubert <bernd.schubert@fastmail.fm>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: "linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	Joanne Koong <joannelkoong@gmail.com>,
	Josef Bacik <josef@toxicpanda.com>
Subject: Re: fuse-io-uring: We need to keep the tag/index
Date: Thu, 3 Oct 2024 16:09:02 +0200	[thread overview]
Message-ID: <e75d6df7-d39b-4186-b319-08b3d1207712@fastmail.fm> (raw)
In-Reply-To: <CAJfpegtpCdGPN=X1_58bpD9eBnnK1gCBKTkGsRqn7cK3wJzk8g@mail.gmail.com>



On 10/3/24 16:04, Miklos Szeredi wrote:
> On Thu, 3 Oct 2024 at 16:02, Miklos Szeredi <miklos@szeredi.hu> wrote:
>>
>> On Thu, 3 Oct 2024 at 15:56, Bernd Schubert <bernd.schubert@fastmail.fm> wrote:
>>
>>> I'm inclined to do xarray, but still to assign an index (in the order of
>>> received FUSE_URING_REQ_FETCH per queue) - should still give O(1).
>>
>> xarray index is unsigned long, while req->unique is u64, which on 32
>> bit doesn't fit.
> 
> I suggest leaving this optimization to a later time.  Less code to
> review and less chance for bugs to creep in.

Well, we need to search - either rbtree or xarray, please not the
existing request_find() with a list search - totally unsuitable for
large number of requests in fly (think of a ring with 32768 entries).
I.e. that points to not using req->unique, but own own index.


Thanks,
Bernd

  reply	other threads:[~2024-10-03 14:09 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-02 21:54 fuse-io-uring: We need to keep the tag/index Bernd Schubert
2024-10-03  9:50 ` Miklos Szeredi
2024-10-03 10:10   ` Bernd Schubert
2024-10-03 12:02     ` Miklos Szeredi
2024-10-03 13:19       ` Bernd Schubert
2024-10-03 13:56         ` Bernd Schubert
2024-10-03 14:02           ` Miklos Szeredi
2024-10-03 14:04             ` Miklos Szeredi
2024-10-03 14:09               ` Bernd Schubert [this message]
2024-10-03 14:26                 ` 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 \
    --in-reply-to=e75d6df7-d39b-4186-b319-08b3d1207712@fastmail.fm \
    --to=bernd.schubert@fastmail.fm \
    --cc=joannelkoong@gmail.com \
    --cc=josef@toxicpanda.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    /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).