MPTCP Linux Development
 help / color / mirror / Atom feed
From: Matthieu Baerts <matttbe@kernel.org>
To: Paolo Abeni <pabeni@redhat.com>, mptcp@lists.linux.dev
Subject: Re: [PATCH mptcp-next v2 0/7] mptcp: rx path refactor
Date: Sat, 21 Dec 2024 12:17:49 +0100	[thread overview]
Message-ID: <f9cbdb1d-07f3-4a60-b6bf-78ac4cba4650@kernel.org> (raw)
In-Reply-To: <cover.1733486870.git.pabeni@redhat.com>

Hi Paolo, Mat,

On 06/12/2024 13:09, Paolo Abeni wrote:
> This is a batch of changes I had sitting in my local tree for a while.
> Why another refactor you may ask? Two main resons:
> 
> - currently the mptcp RX path introduces quite a bit of 'exceptional'
>  accounting/locking processing WRT to plain TCP, adding up to the
>  implementation complexity in a misurable way
> - the performance gap WRT plain TCP for single subflow connections is
>  quite measurable.
> 
> The present refactor addresses both the above items: most of the
> additional complexity is dropped, and single stream performances
> increase measurably - from 55Gbps to 71Gbps in my loopback test. As a
> reference, plain TCP is around 84Gps on the same host.
> 
> The above comes to a price: the patch are invasive, even in subtle ways:
> the chance of destabilizing the implementation is real (ence the
> additional, intentional '-next' into the subj).
> 
> In any case keeping the patch hidden for longer was not going to do any
> good, so here we are.

Thank you for the patches and the reviews!

Patches 2 and 3 are now in the "fixes for net", while the others are in
"feat. for next". I think patch 1 can go to "Fixes for net", any objections?

New patches for t/upstream-net and t/upstream:
- d443f83de23d: mptcp: fix recvbuffer adjust on sleeping rcvmsg
- 11d4943d66ee: mptcp: don't always assume copied data in
mptcp_cleanup_rbuf()
- Results: 3a0f411ba1c5..2116e71814b7 (export-net)
- Results: df3193ae83eb..953b0d388720 (export)

Tests are now in progress:

- export-net:
https://github.com/multipath-tcp/mptcp_net-next/commit/047c2f99575350d9971b6257f96ce5f734f0186a/checks

New patches for t/upstream:
- 972d8a5b7f20: mptcp: prevent excessive coalescing on receive
- 0b0a25a24d21: mptcp: consolidate subflow cleanup
- 533bb69f1b0d: mptcp: move the whole rx path under msk socket lock
protection
- c5d13b230497: mptcp: cleanup mem accounting
- a564b9923a94: net: dismiss sk_forward_alloc_get()
- Results: 953b0d388720..9213903d77ba (export)

Tests are now in progress:

- export:
https://github.com/multipath-tcp/mptcp_net-next/commit/6aae9c8bd8361dd90a7def87459ca0173915c56c/checks

Cheers,
Matt
-- 
Sponsored by the NGI0 Core fund.


      parent reply	other threads:[~2024-12-21 11:17 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-06 12:09 [PATCH mptcp-next v2 0/7] mptcp: rx path refactor Paolo Abeni
2024-12-06 12:10 ` [PATCH mptcp-next v2 1/7] mptcp: prevent excessive coalescing on receive Paolo Abeni
2024-12-10 12:03   ` Matthieu Baerts
2024-12-21 10:00     ` Matthieu Baerts
2024-12-27  9:40       ` Paolo Abeni
2024-12-30 18:24         ` Matthieu Baerts
2024-12-06 12:10 ` [PATCH mptcp-next v2 2/7] tcp: fix recvbuffer adjust on sleeping rcvmsg Paolo Abeni
2024-12-06 12:10 ` [PATCH mptcp-next v2 3/7] mptcp: don't always assume copied data in mptcp_cleanup_rbuf() Paolo Abeni
2024-12-06 12:10 ` [PATCH mptcp-next v2 4/7] mptcp: consolidate subflow cleanup Paolo Abeni
2024-12-06 12:11 ` [PATCH mptcp-next v2 5/7] mptcp: move the whole rx path under msk socket lock protection Paolo Abeni
2024-12-06 12:11 ` [PATCH mptcp-next v2 6/7] mptcp: cleanup mem accounting Paolo Abeni
2024-12-07  1:45   ` Mat Martineau
2024-12-10  9:00     ` Paolo Abeni
2024-12-06 12:11 ` [PATCH mptcp-next v2 7/7] net: dismiss sk_forward_alloc_get() Paolo Abeni
2024-12-06 13:17 ` [PATCH mptcp-next v2 0/7] mptcp: rx path refactor MPTCP CI
2024-12-06 16:41 ` Paolo Abeni
2024-12-21  2:12 ` Mat Martineau
2024-12-21 11:17 ` Matthieu Baerts [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=f9cbdb1d-07f3-4a60-b6bf-78ac4cba4650@kernel.org \
    --to=matttbe@kernel.org \
    --cc=mptcp@lists.linux.dev \
    --cc=pabeni@redhat.com \
    /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