[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id:
<170633222951.22327.8113682508825854536.git-patchwork-notify@kernel.org>
Date: Sat, 27 Jan 2024 05:10:29 +0000
From: patchwork-bot+netdevbpf@...nel.org
To: Kuniyuki Iwashima <kuniyu@...zon.com>
Cc: davem@...emloft.net, edumazet@...gle.com, kuba@...nel.org,
pabeni@...hat.com, ivan@...udflare.com, kuni1840@...il.com,
netdev@...r.kernel.org
Subject: Re: [PATCH v5 net-next 0/5] af_unix: Random improvements for GC.
Hello:
This series was applied to netdev/net-next.git (main)
by Jakub Kicinski <kuba@...nel.org>:
On Tue, 23 Jan 2024 09:08:51 -0800 you wrote:
> If more than 16000 inflight AF_UNIX sockets exist on a host, each
> sendmsg() will be forced to wait for unix_gc() even if a process
> is not sending any FD.
>
> This series tries not to impose such a penalty on sane users who
> do not send AF_UNIX FDs or do not have inflight sockets more than
> SCM_MAX_FD * 8.
>
> [...]
Here is the summary with links:
- [v5,net-next,1/5] af_unix: Annotate data-race of gc_in_progress in wait_for_unix_gc().
https://git.kernel.org/netdev/net-next/c/31e03207119a
- [v5,net-next,2/5] af_unix: Do not use atomic ops for unix_sk(sk)->inflight.
https://git.kernel.org/netdev/net-next/c/97af84a6bba2
- [v5,net-next,3/5] af_unix: Return struct unix_sock from unix_get_socket().
https://git.kernel.org/netdev/net-next/c/5b17307bd078
- [v5,net-next,4/5] af_unix: Run GC on only one CPU.
https://git.kernel.org/netdev/net-next/c/8b90a9f819dc
- [v5,net-next,5/5] af_unix: Try to run GC async.
https://git.kernel.org/netdev/net-next/c/d9f21b361333
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
Powered by blists - more mailing lists