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>, Amir Goldstein <amir73il@gmail.com>
Cc: Bernd Schubert <bschubert@ddn.com>,
	linux-fsdevel@vger.kernel.org, Dharmendra Singh <dsingh@ddn.com>
Subject: Re: [RFC PATCH 00/13] fuse uring communication
Date: Thu, 8 Jun 2023 23:31:28 +0200	[thread overview]
Message-ID: <2ac5a016-505c-125a-a431-8d7547347a65@fastmail.fm> (raw)
In-Reply-To: <CAJfpegtL3NXPNgK1kuJR8kLu3WkVC_ErBPRfToLEiA_0=w3=hA@mail.gmail.com>



On 6/7/23 16:20, Miklos Szeredi wrote:
> On Thu, 23 Mar 2023 at 12:55, Amir Goldstein <amir73il@gmail.com> wrote:
>>
>> On Thu, Mar 23, 2023 at 1:18 PM Bernd Schubert
>> <bernd.schubert@fastmail.fm> wrote:
> 
>>> there were several zufs threads, but I don't remember discussions about
>>> cache line - maybe I had missed it. I can try to read through the old
>>> threads, in case you don't have it.
>>
>> Miklos talked about it somewhere...
> 
> It was a private exchange between Amir and me:
> 
>      On Tue, 25 Feb 2020 at 20:33, Miklos Szeredi <miklos@szeredi.hu> wrote
>      > On Tue, Feb 25, 2020 at 6:49 PM Amir Goldstein <amir73il@gmail.com> wrote:
>      [...]
>      > > BTW, out of curiosity, what was the purpose of the example of
>      > > "use shared memory instead of threads"?
>      >
>      > In the threaded case there's a shared piece of memory in the kernel
>      > (mm->cpu_bitmap) that is updated on each context switch (i.e. each
>      > time a request is processed by one of the server threads).  If this is
>      > a big NUMA system then cacheline pingpong on this bitmap can be a real
>      > performance hit.
>      >
>      > Using shared memory means that the address space is not shared, hence
>      > each server "thread" will have a separate "mm" structure, hence no
>      > cacheline pingpong.
>      >
>      > It would be nice if the underlying problem with shared address space
>      > could be solved in a scalable way instead of having to resort to this
>      > hack, but it's not a trivial thing to do.  If you look at the
>      > scheduler code, there's already a workaround for this issue in the
>      > kernel threads case, but that doesn't work for user threads.

Ah, thank you! I can quote this mail here then for the next version.

Thanks,
Bernd

PS: I get currently distracted by other work, I hope I can get back to 
fuse by tomorrow.

      reply	other threads:[~2023-06-08 21:31 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-21  1:10 [RFC PATCH 00/13] fuse uring communication Bernd Schubert
2023-03-21  1:10 ` [PATCH 01/13] fuse: Add uring data structures and documentation Bernd Schubert
2023-03-21  1:10 ` [PATCH 02/13] fuse: rename to fuse_dev_end_requests and make non-static Bernd Schubert
2023-03-21  1:10 ` [PATCH 03/13] fuse: Move fuse_get_dev to header file Bernd Schubert
2023-03-21  1:10 ` [PATCH 04/13] Add a vmalloc_node_user function Bernd Schubert
2023-03-21 21:21   ` Andrew Morton
2023-03-21  1:10 ` [PATCH 05/13] fuse: Add a uring config ioctl and ring destruction Bernd Schubert
2023-03-21  1:10 ` [PATCH 06/13] fuse: Add an interval ring stop worker/monitor Bernd Schubert
2023-03-23 10:27   ` Miklos Szeredi
2023-03-23 11:04     ` Bernd Schubert
2023-03-23 12:35       ` Miklos Szeredi
2023-03-23 13:18         ` Bernd Schubert
2023-03-23 20:51           ` Bernd Schubert
2023-03-27 13:22             ` Pavel Begunkov
2023-03-27 14:02               ` Bernd Schubert
2023-03-23 13:26         ` Ming Lei
2023-03-21  1:10 ` [PATCH 07/13] fuse: Add uring mmap method Bernd Schubert
2023-03-21  1:10 ` [PATCH 08/13] fuse: Move request bits Bernd Schubert
2023-03-21  1:10 ` [PATCH 09/13] fuse: Add wait stop ioctl support to the ring Bernd Schubert
2023-03-21  1:10 ` [PATCH 10/13] fuse: Handle SQEs - register commands Bernd Schubert
2023-03-21  1:10 ` [PATCH 11/13] fuse: Add support to copy from/to the ring buffer Bernd Schubert
2023-03-21  1:10 ` [PATCH 12/13] fuse: Add uring sqe commit and fetch support Bernd Schubert
2023-03-21  1:10 ` [PATCH 13/13] fuse: Allow to queue to the ring Bernd Schubert
2023-03-21  1:26 ` [RFC PATCH 00/13] fuse uring communication Bernd Schubert
2023-03-21  9:35 ` Amir Goldstein
2023-03-23 11:18   ` Bernd Schubert
2023-03-23 11:55     ` Amir Goldstein
2023-06-07 14:20       ` Miklos Szeredi
2023-06-08 21:31         ` Bernd Schubert [this message]

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=2ac5a016-505c-125a-a431-8d7547347a65@fastmail.fm \
    --to=bernd.schubert@fastmail.fm \
    --cc=amir73il@gmail.com \
    --cc=bschubert@ddn.com \
    --cc=dsingh@ddn.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).